Speech-to-text in language services and learning: an update (rescheduled)

This presentation has been rescheduled due to unanticipated conflicts. On March 4th at 4:00 pm Central European Time (10 am Eastern Standard Time), I'll be presenting an overview of some popular and/or possible platforms for generating text from spoken words for professional work and language learning. As those who have followed this blog for years know, I have written quite a bit about this in the past and done a number of videos for demonstration and instruction using various platforms, but this is a field subject to frequent change and many new developments, so it is difficult sometimes to understand the value of one tool versus another for different applications.

The webinar is available free to anyone interested, and there will be time for questions afterward. We will compare and contrast Dragon NaturallySpeaking, iOS-based applications (including Hey memoQ), Google Chrome and Windows 10 for speech recognition work in translation and transcription, discussing some of the advantages and trade-offs with each platform working in translation environments and text-editing software, and the range of languages covered by each. Join us, and see if there are good fits for your speech recognition needs!

You can register here for the discussion.

Review: the Plantronics Voyager Legend monoaural headset for translation

Ergonomics are often a challenge with the microphones used for dictated translation work. I've used quite a few over the years, usually with USB connections to my computer, though I've also had a few Logitech wireless headphones with integrated mikes that performed well. However, all of them have had some disadvantages.

The country where I live (Portugal) has a rather warm climate for more than a few months of the year. Wearing headphones can get rather uncomfortable on a hot day, and even on a cold one, the pressure on my ears starts to drive me nuts after an hour or so.

Desktop microphones seem like a good solution, and I get good results with my Blue Yeti. But sometimes, when I turn my head to look at something, the pickup is not so good, and my dictation is transcribed incorrectly.

The Hey memoQ app released by memoQ Translation Technologies Ltd. underscored the ergonomic challenges of dictation for me; the app uses iOS devices to access their speech recognition features, and positioning a phone well in such a way that one can still make use of a keyboard is not easy. And trying to connect a microphone or headset by cable to the dodgy Lightning port on my iPhone 7 is usually not a good experience.

So I was intrigued by a recommendation of Plantronics headsets from Dragos Ciobanu of Leeds University (also the author of the E-learning Bakery blog). A specific model mentioned by someone who had attended a dictation workshop with him recently was the Plantronics Voyager Legend, though when I asked Dragos about his experience, he spoke mostly about the Plantronics Voyager 5200, which is a little more expensive. I decided to go "cheap" for my first experience with this sort of equipment and ordered the Voyager Legend from Amazon in Spain. I did so with some trepidation, because the reviews I read were not entirely positive.

The product arrived in simple packaging which led me to think that the Amazon review which suggested the "new" products sold might in fact be refurbished. But in the EU, all electronic gear comes with a two-year warranty, so I don't worry too much about that.

Complaints I read in the reviews about a short charger cable seem ridiculous; the cable I received was over half a meter long, and like anyone who has computers these days, I have more USB extension cords than I know what to do with should I require a longer cable for charging. The magnetic coupler for charging has a female mini-USB port, so it can be attached to another cable as well. Power connections include the most common EU two-pronged charger, the 3-pole UK charger and one for a car's cigarette lighter.

The package also included extra earpieces and covers of different sizes to customize the fit on one's ear.

I tested the microphone first with my laptop; the device was recognized easily, and the results with Dragon NaturallySpeaking were excellent. Getting the connection to my iPhone 7 proved more difficult, however. I read the Getting Started instructions carefully, tried updating the firmware (not necessary - everything was current) and tried various switching and reboot tricks, all to no avail.

Finally, I called the technical support line in the US in total frustration. I didn't expect an answer since it was still the wee hours of the morning in the US, but someone at a support call center did answer the phone. He instructed me to press and hold the "call" button on the device until its LED begins to flash blue and red.


I did that, and when the LED began flashing, "PLT_Legend" appeared in the list of available devices on my iPhone. Then I was ready to test the Voyager Legend for dictated translation with Hey memoQ.

Because I work with German and English, I rely on Dragon NaturallySpeaking for my dictation, and the iOS-based dictation of Hey memoQ will never compete with that. But I am very interested in testing and demonstrating the integrated memoQ app, because many other languages, such as Portuguese, are not available for speech recognition in Dragon NaturallySpeaking or any other readily accessible speech recognition solution of its class.

As I suspected, my dictation in Hey memoQ (and other iOS applications) was easier with the Voyager Legend. This is the first hardware configuration I have tested that really seems like it would offer acceptable ergonomics for Hey memoQ with my phone. And I can use it for Skype calls, listening to my audio books and other things, so I consider the Plantronics Voyager Legend to be money well spent. Now I'll see how it holds up for long sessions of dictated legal translation. The product literature and a little voice in my ear both claim that the device can operate for seven hours of speaking time on a battery charge, and the 90 minutes required for a full recharge will work well enough with the breaks I take in that time anyway.

Of course there are many Bluetooth microphone devices which can be used with speech recognition applications, but what distinguishes this one is its great comfort of wear and the secure fit on my ear. I look forward to a closer acquaintance.

Using analog microphones with newer iPhones

Microphone quality makes a great difference in the quality of speech recognition results. And although the microphones integrated in iOS devices are generally good and give decent results, positioning the device in a way that is ergonomically viable for efficient dictated translation - and concurrent keyboard use - is not always so easy. This is a potential barrier to the effective use of Hey memoQ speech recognition.

So a good external microphone may be needed. But with recent iPhone models lacking a separate microphone jack and using the lightning port for both charging and microphone input, connecting that external microphone might not be as simple as one assumes. Especially not someone like me, who is rather ignorant of the different kinds of 3.5 mm audio connections. I have had a few failures so far trying to link my good headset to the iPhone 7.

Colleague Jim Wardell is not only the most experienced speech recognition expert for translation whom I am privileged to know; he is also a musician with extensive experience in microphones of all kinds and their connections. And recently he was kind enough to share the video below with me to clear up some misunderstandings about how to connect some good analog equipment to use with Hey memoQ on an iPhone 7 or later:

Hacking the "Hey memoQ" dictation commands

In the initial release of the Hey memoQ dictation feature in memoQ version 8.7.3, it's a bit inconvenient to deal with command configuration. Unlike most configurations in memoQ, the dictation commands cannot yet be exported as a light resource and shared with other users, nor can a configuration for generic German, for example, be easily transferred to a desired variant such as "ger-DE" or "ger-CH". Surely this will be addressed soon, but at the moment it's a bit of a nuisance.

But fear not... there is usually a backdoor to hack memoQ configurations, and this is no exception.

The screenshot above shows the path to the current configuration file for dictation commands. The XML file contains all the configured commands for all the memoQ languages and variants, including those of no interest whatsoever.

Deep inside the Hey memoQ dictation command file with Notepad++

A peek inside the XML file reveals that the dictation commands are structured as key-value pairs. And here it is possible to enter the text for dictation commands, simply by typing the desired text between the string tags inside the Value tags.

A configuration (Commands set) for one variant of a language - such as generic Portuguese - can also be copied to other variants - such as Brazilian or European Portuguese, saving the trouble of re-entering everything laboriously in the configuration dialog within memoQ.

I made a copy of the XML configuration and edited it to have only the variants of English and German that were of interest to me. Then I copied this file over the one in the memoQ configuration directory shown in the screenshot above. When I restarted memoQ, the file bloated a bit; upon examining it, I saw that all the deleted languages had been restored after the ones I had left in the edited file, but the new file was still only 247 KB in size because the senseless copying of English commands to the other languages was gone.

A customized XML file can be shared with other users, who can use it to replace the existing configuration file and probably save time configuring their languages and variants of interest. My file with generic English, EN-US, EN-UK, generic German and DE-DE is here.

Deutsche Kommandos für „Hey memoQ“

Mit der memoQ Version 8.7 hat memoQ Translation Technologies Ltd. (ehemals „Kilgray“ – „mQtech“ unten) eine kostenlose, integrierte Spracherkennung eingeführt, die für die Arbeit in vielen Sprachen eine wesentliche Effizienzsteigerung verspricht. Für die Arbeit in deutscher Sprache soll es von vornherein klar gestellt werden: Dragon NaturallySpeaking (DNS) ist und bleibt für die vorhersehbare Zeit die bessere Wahl. Das gleiche gilt für alle Sprachen, die von DNS (in der aktuellen Version 15) unterstützt sind: Deutsch, Englisch, Spanisch, Französisch, Italienisch und Niederländisch.

Aber für die slawischen Sprachen, nordischen Sprachen, sonstigen romanischen Sprachen, Arabisch u.v.m. sind andere Lösungen gefragt, wenn man mit Spracherkennung arbeiten will. Vor etwa 4 Jahren, als ich angefangen habe, solche Lösungen zu erforschen, waren diese für „exotische“ Sprachen wie Russisch oder europäisches Portugiesisch als Teil der Übersetzungsarbeiten kaum gedacht; heute gibt es vielfältige halbgute Möglichkeiten, zu denen jetzt auch „Hey memoQ“ gehört. Noch warten wir auf Lösungen auf der Ebene von DNS für die sonstigen Sprachen und noch lange werden wir sicher warten, bis gute Erkennungsqualität mit einfach erweiterbarem Wortschatz und flexiblen, konfigurierbaren Kommandos für die Systemsteuerung für Sprachen wie Dänisch oder Hindi allgemein verfügbar sind. Zur Zeit sind wir nicht mal so weit mit Englisch, wenn man z.B. die Diktierfunktion auf Handys betrachtet. Spracherkennung ohne eigenständig erweiterbarem Wortschatz ist und bleibt eine Technologie auf Krücken.

Aber die Krücken bei Hey memoQ sind erstmal nicht schlecht für eine aufkommende Technologie. Die mit der 8.7er Version von memoQ freigegebene App ist m.E. noch „Beta“ – was kann man sonst sagen, wenn nur für Englisch die Steuerungskommandos standardmäßig konfiguriert sind? – aber für den Stand der derzeit zahlbaren Technologie ist die von mQtech eingeführte Lösung die beste in der Klasse, sogar mit einem tauglichen Umgehungslösung für das Problem des nichterweiterbaren Wortschatzes, nämlich die Möglichkeit, sprachgesteuert die ersten neuen Treffer aus der Ergebnisliste der Terminologie, Korporasuche, Nontranslatables usw. in den Zieltext einzufügen. Wenn man sowieso vernünftige Terminologiearbeit leistet und ein memoQ-Glossar mit den nötigen Sonderbegriffen ausstattet, kann man schon ziemlich gut arbeiten. (Und wer eventuell eine Einweisung in die statistisch basierte Erfassung der häufigen Begriffe aus einem Dokument bzw. einer Dokumentensammlung benötigt, kann sich hier informieren.)

Hey memoQ hat auch andere Alleinstellungsmerkmale, u.a. einen Wechsel der Erkennungssprache, wenn man den Cursor im Textfeld für die andere Arbeitssprache setzt. Also wenn ich z.B. Englisch als Zieltext diktiere, will aber einen Tippfehler im deutschen Ausgangstext korrigieren oder vielleicht den gesamten Text nach einem bestimmten Wort im Ausgangstext filtrieren, wechselt die von Hey memoQ verstandene Sprache von Englisch auf Deutsch, wenn ich bloß auf Zieltextseite klicke. So geht das auch bei jedem unterstützten Sprachpaar. Nicht schlecht.

Wer bereits meckert, dass diese derzeit auf Apple iOS basierende Lösung nicht für die beliebten Android-Handys verfügbar ist, begreift die Realität der Softwareentwicklung bzw. Produktentwicklung einfach nicht. Schon vor mQtech mit der Entwicklung dieser Lösung begonnen hat, habe ich selber aus persönlichem Anlass die möglichen Application Programming Interfaces (APIs) untersucht, und bei den meisten war die Kommandosteuerung, wie sie bei Hey memoQ zu finden ist, nicht verfügbar. In den meisten Fällen nur die Übertragung eines gesprochenen und transkribierten Textes. Aber das hat wir bereits. Bei myEcho zum Beispiel. Oder auch die Lösung für Chrome-Spracherkennung in jedem Windows- oder Linux-Programm. Was wir dringend brauchen ist nicht das Bier von gestern. Wir brauchen zukunftsweisende Prototypen, die die Entwicklung der branchenüblichen Technologien wie memoQ, SDL Trados Studio, WordFast und andere in eine bessere Richtung treiben, und das macht schon Hey memoQ. Also ein dickes Lob an das memoQ-Team und seinen deutschen Entwicklungschef :-)

Aber auch mit einem deutschen Entwicklungschef, ist der Zeitdruck manchmal so, dass man vorläufig keine konfigurierten Steuerungskommandos mit der ersten Release-Version freigibt, wahrscheinlich weil das eigentlich aufwändiger ist, als die meisten Leute sich glauben würden. In jeder Sprache. Wer zum Beispiel Polnisch diktieren will und nicht nur die gesprochenen Phrasen ins Textfeld transkribiert haben will, sondern auch sprachgesteuert den Text editieren oder Filterkommandos oder Konkordanzsuche ausführen will, muss erstmal polnische Kommandos im Programm einrichten. Und da stoßt man oft unerwartet an die Grenzen und Merkwürdigkeiten der individuellen Erkennungstechnologie. Eine gewählte Phrase kann, zum Beispiel, einer sehr häufigen Phrase ähneln, so dass oft diesen anderen Text geschrieben wird, wenn man eigentlich ein Kommando ausführen lassen wollte. Also sind ungewöhnliche aber erkennbare Texte oft die beste Wahl für Kommandotexte. Meine erprobten Kommandotexte für Deutsch sind unten als Screenshot angegeben. Wie man gleich merkt, ist das zu konfiguriende Dialog noch nicht für die deutsche Benutzeroberfläche lokalisiert. In kommenden Versionen wird das natürlich der Fall sein. Aber ob irgendwann aus Ungarn die Bearbeitungskommandos für Griechisch vorkonfiguriert kommen werden, kann ich nicht raten. Selber konfigurieren kann man sie aber heute schon, wenn man Geduld hat.

Noch zu bemerken: die iOS-Spracherkennung benötigt gute Internet-Bandbreite, da der Erkennungsserver im Cloud liegt. Datenschutz, Datenschutz, ja, ja. Sparen Sie mir den Vortrag bitte und lassen sie diese Technologie sich erstmal weiter entwickeln. Die Fragen zum Datenschutz waren schon vor einigen Jahren ausreichend von deutschen Vertretern der Firma Nuance beantwortet, und sogar die verrückten US-Behörden haben den Einsatz solcher Technologie intern freigegeben. Aber in Deutschland dreht sich die Welt anders, und gut so :-) Übrigens erlebe ich mehr Erfolg, wenn ich in kurzen, sogar dramatischen Phrasen spreche, und nicht in langen, wortreichen Sätzen. Eine ganz andere notwendige Vorgehensweise als mit DNS, zum Beispiel. Wer zu schnell spricht, merkt auch schnell, dass Wörter ausgelassen werden. Nichts mit Hey memoQ zu tun, sondern Bestandteil des Standes der Technik bei iOS-Spracherkennung sowie bei manchen anderen Technologien dieser Gattung.

Und jetzt die Ansicht meiner selbstkonfigurierten Hey memoQ Steuerungskommandos für Deutsch. Wem sich meine Wortwahl nicht gefällt, kann sich was Besseres aussuchen und hoffentlich testen und danach in den Kommentaren unten allen deutschsprachigen Kollegen mitteilen.

Die iOS-Kommandos für Interpunktion u.v.m. habe ich auf Basis der von Apple publizierten MacOS-Kommandos erforscht; es gibt in einzelnen Fällen leichte Unterschiede (d.h. man muss ein wenig experimentieren, bis man auf das richtige Kommando stoßt - falls es tatsächlich existiert), aber hiermit hat man einen guten Anfang für Sonderzeichen usw. wie ich neulich in einem englischen Blogbeitrag erklärt habe. Für fehlende Informationen kann man mQtech keine Schuld zuweisen, wenn nicht mal der iOS-Hersteller Apple die vollständige und richtige Liste mitteilt. Aber mit viel Zeit wird der Kuchen sicher gut gebacken!

Your language in Hey memoQ: recognition information for speech

There are quite a number of issues facing memoQ users who wish to make use of the new speech recognition feature – Hey memoQ – released recently with memoQ version 8.7. Some of these are of a temporary nature (workarounds and efforts to deal with bugs or shortcomings in the current release which can reasonably be expected to change soon), others – like basic information on commands for iOS dictation and what options have been implemented for your language – might not be so easy to work out. My own research in this area for English, German and Portuguese has revealed a lot of errors in some of the information sources, so often I have to take what I find and try it out in chat dictation, e-mail messages or the Notes app (my favorite record-keeping tool for such things) on the iOS device. This is the "baseline" for evaluating how Hey memoQ should transcribe text in a given language.

But where do you find this information? One of the best way might be a Google Advanced Search on Apple's support site. Like this one, for example:

The same search (or another) can be made by adding the site specification after your search terms in an ordinary Google search:

The results lists from these searches reveal quite a number of relevant articles about iOS dictation in English. And by hacking the URLs on certain pages and substituting the language code desired, one can get to the information page on commands available for that language. Examples include:

• German (de-de)
• Polish (pl-pl)
• Russian (ru-ru)
• Arabic (ar-ae)
• Japanese (ja-jp)
• Greek (el-gr)

All the same page, with slightly modified URLs.

The Mac OS information pages are also a source of information on possible iOS commands that one might not find so easily otherwise. An English page with a lot of information on punctaution and symbols is here: https://support.apple.com/en-us/HT202584

The same information (if available) for other languages is found just by tweaking the URL:

• German (de-de)
• Portuguese (pt-pt, there is also a pt-br page, but I haven't read both to check differences)
• Polish (pl-pl)
• Norwegian (that's a no-no)
• Arabic (ar-ae)
• Turkish (tr-tr)
• French (fr-fr)
• Thai (th-th, see also this commentary on another site)

and so on. Some guidance on Apple's choice of codes for language variants is here, but I often end up getting to where I want to go by guesswork. The Microsoft Azure page for speech API support might be more helpful to figure out how to tweak the Apple Support URLs.

When you edit the commands list, you should be aware of a few things to avoid errors.

• The current command lists in the first release may contain errors, such as mistakenly typing "phrase" in angular brackets as shown in the first example above; on editing, the commands that are followed by a phrase do not show the placeholder for that phrase, as you see in the example marked "2".
• Commands must be entered without quotation marks! Compare the marked examples 1 and 2 above. If quotes are typed when editing a command, this will not be revealed by the appearance of the command; it will look OK but won't work at all until the quote marks are removed by editing.
• Command creation is an iterative process that may entail a lot of frustrating failures. When I created my German command set, I started by copying some commands used for editing by Dragon NaturallySpeaking, but often the results were better if I chose other words. Sometimes iOS stubbornly insists on transcribing some other common expression, sometimes it just insists on interpreting your command as a word to transcribe. Just be patient and try something else.

The difficulties involved in command development at this stage are surely why only one finished command set (for the English variants) for memoQ-specific commands was released at first. But that makes it all the more important to make command sets "light resources" in memoQ, which can be easily exported and exchanged with others.

At the present stage, I see the need for developing and/or fixing the Hey memoQ app in the following ways:

• Fix obvious bugs, which include: 

• The apparently non-functional concordance insertions. In general, more voice control would be helpful in the memoQ Concordance.
• Capitalization errors which may affect a variety of commands, like Roman numerals, ALL CAPS, title capitalization (if the first word of the title is not at the start of the segment), etc.
• Dodgy responses to the commands to insert spaces, where it is often necessary to say the command twice and get stuck with two spaces, because a single command never responds properly by inserting a space. Why is that needed? Well, otherwise you have to type a space on the keyboard if you are going to use a Translation Results insertion command to insert specialized terminology, auto-translation rule results, etc. into your text. 

• Address some potentially complicated issues, like considering what to do about source language text handling if there is no iOS support for the source language or the translator cannot dictate commands effectively in that language. I can manage in German or Portuguese, but I would be really screwed these days if I had to give commands in Russian or Japanese.
• Expand dictation functionality in environments like the QA resolution lists, term entry dialog, alignment editor and other editors.
• Look for simple ideas that could maximize returns for programming effort invested, like the "Press" command in Dragon NaturallySpeaking, which enables me to insert tags, for example, by saying "Press F9". This would eliminate the need for some commands (like confirmation and all the Translation Results insertion commands) and open up a host of possibilities by making keyboard shortcuts in any context controllable by voice. I've been thinking a lot about that since talking to a colleague with some pretty tough physical disabilities recently.

Overall, I think that Hey memoQ represents a great start in making speech recognition available in a useful way in a desktop translation environment tool and making the case for more extensive investments in speech recognition technology to improve accessibility and ergonomics for working translators.

Of course, speech recognition brings with it a number of different challenges for reviewing work: mistakes (or "dictos" as they are sometimes called, a riff on keyboard "typos") are often harder to catch, especially if one is reviewing directly after translating and the memory of intended text is perhaps fresh enough to override in perception what the eye actually sees. So maybe before long we'll see an integrated read-back feature in memoQ, which could also benefit people who don't work with speech recognition. 

Since I began using speech recognition a lot for my work (to cope with occasionally unbearable pain from gout), I have had to adopt the habit of reading everything out loud after I translate, because I have found this to be the best way to catch my errors or to recognize where the text could use a rhetorical makeover. (The read-back function of Dragon NaturallySpeaking in English is a nightmare, randomly confusing definite and indefinite articles, but other tools might be usable now for external review and should probably be applied to target columns in an exported RTF bilingual file to facilitate re-import of corrections to the memoQ environment, though the monolingual review feature for importing edited target text files and keeping project resources up-to-date is also a good option.)

As I have worked with the first release of Hey memoQ, I have noticed quite a few little details where small refinements or extensions to the app could help my workflow. And the same will be true, I am sure, with most others who use this tool. It is particularly important at this stage that those of us who are using and/or testing this early version communicate with the development team (in the form of e-mail to memoQ Support - support@memoq.com - with suggestions or observations). This will be the fastest way to see improvements I think.

In the future, I would be surprised if applications like this did not develop to cover other input methods (besides an iOS device like an iPhone or iPad). But I think it's important to focus on taking this initial platform as far as it can go so that we can all see the working functionality that is missing, so that as the APIs for relevant operating systems develop further to support speech recognition (especially the Holy Grail for many of us, trainable vocabulary like we have in Dragon NaturallySpeaking and a very few other applications). Some of what we are looking for may be in the Nuance software development kits (SDKs) for speech recognition, which I suggested using some years ago because they offer customizable vocabularies at higher levels of licensing, but this would represent a much greater and more speculative investment in an area of technology that is still subject to a lot of misunderstanding and misrepresentation.

"Hey memoQ" command tests

In my last post on the release of memoQ 8.7 with its new, integrated speech recognition feature I included a link to a long, boring video record of my first tests of the speech recognition facility, most of which consisted of testing various spoken iOS commands to generate text symbols, change capitalization, etc. I tested some of the integrated commands that are specific to memoQ, but not in an organized way really.

In a new testing video, I attempt to show all the memoQ-specific spoken command types and how the commands are affected by the environment (in this case I mean whether the cursor is on the target text side or the source text side or in some other place in the concordance, for example).

Most of the spoken commands work rather well, except for insertion from the concordance, which I could not get to work at all. When the cursor is in a source text cell, commands have to be given in the source text language currently, which is sure to prove interesting for people who don't speak their source language with a clean accent. Right now it's even more interesting, because English is the only language with a ready-made command list; other languages have to "roll their own" for now, which is a bit of a trial-and-error thing. I don't even want to think how this is going to work if the source language isn't supported at all; I think some thought had to be given to how to use commands with source text. I assume if it's copied to the target side it will be difficult to select unless, with butchered pronunciation, the text also happens to make sense in the target language.


It's best to watch this video on YouTube (start it, then click "YouTube" at the bottom of the running video). There you'll find a time code index in the description (after you click SEE MORE) which will enable you to navigate to specific commands or other things shown in the test video.

My ongoing work with Hey memoQ make it clear that what I call "mixed mode" (dictation with concurrent use of the keyboard) is the best and (actually) necessary way to use this feature. The style for successful dictation is also quite different than the style I need to use with Dragon NaturallySpeaking for best results. I have to discipline myself to speak more in short phrases, less in longer ones, much less in long sentences, which may cause some text to be dropped.

There is also an issue with Translation Results insertions and the lack of spaces before them; the command to insert a space ("spacebar" in English) is dodgy, so I usually have to speak it twice and end up with a superfluous space. The video shows my workaround for this in one part: I speak a filler word (in one case I tried "dummy" which was rendered as "dumb he") and then select it later and insert an entry from the Translation Results pane over the selected text. This is in fact how we can deal with specialist terminology not recognized by the current speech dictionary until it becomes possible to train new words some day.

The sound in the video (spoken commands) is also of variable quality; with some commands I had to turn my head toward the iPhone on its little tripod next to my laptop, which caused the pickup of that speech to be bad on the built-in microphone on the laptop's screen. So this isn't a Hollywood-class recording; it's simply a slightly edited record of some of my tests to give other memoQ users some idea of what they can expect from the feature right now.

Those who will be dictating in supported languages other than English need some patience right now. It's not always easy coming up with commands that will be recognized easily but which are unlikely to occur as words to be transcribed in typical dictation work. During the beta test of Hey memoQ I used some bizarre and unusual German words which just happened to be recognized. I'm developing a set of more normal-sounding commands right now, but it's a work in progress.

The difficulties I am encountering making up new command phrases (or changing the English ones in some cases) simply reinforce my belief that these command lists should be made into portable light resources as soon as possible.

I am organizing summary tables of the memoQ-specific commands and useful iOS commands for symbols, capitals, spacing, etc. comparing their performance in other iOS apps with what we see right now in Hey memoQ.

Update: the summary file for English is available here. I will post links here for any other languages I can prepare later.

Integrated iOS speech recognition in memoQ 8.7

Today, memoQ Translation Technologies (the artists formerly known as "Kilgray") officially released their iOS dictation app along with memoQ version 8.7, making that popular translation environment tool the first on the desktop to offer free integrated speech recognition and control.

My initial tests of the release version are encouraging. Some bugs with capitalization which I identified with the beta test haven't been fixed yet, and some special characters which work fine in the iOS Notes app don't work at all, but on the whole it's a rather good start. The control commands implemented for memoQ work far better than I expected at this stage. I've got a very boring, clumsy (and unlisted) video of my initial function tests here if anyone cares to look.

Before long, I'll release a few command cheat sheets I've compiled for English (update: it's HERE), German and Portuguese, which show which iOS dictation functions are implemented so far in Hey memoQ and which don't perform as expected. There are no comprehensive lists of these commands, and even the ones that claim to cover everything have gaps and errors, which one can only sort out by trial and error. This isn't an issue with the memoQ development team for the most part, but rather of Apple's chaotic documentation.

The initial release only has a full set of commands implemented in English. Those who want to use control commands for navigating, selecting, inserting, etc. will have to enter there own localized commands for now, and this too involves some trial and error to come up with a good working set. And I hope that before long the development team will implement the language-specific command sets as a shareable light resources. That will make it much easier to get all the available languages sorted out properly for productive work.

I am very happy with what I see at the start. Here are a few highlights of the current state of Hey memoQ dictation:

• Bilingual dictation, with source language dictation active when the cursor is on the source side and target language dictation active when the cursor is on the target side. Switching languages in my usual dictation tool - Dragon NaturallySpeaking - is a total pain in the butt.
• No trainable vocabulary at present (an iOS API limitation), but this is balanced in a useful way by commands like "insert first" through "insert ninth", which enable direct insertion of the first nine items in the Translation Results pane. Thus is you maintain good termbases, the "no train" pain is minimized. And you can always work in "mixed mode" as I usually do, typing what is not convenient to speak and using keyboard shortcuts for commands not yet supported by voice control, like tag insertion.
• Microphones connected (physically or via Bluetooth) with the iPhone or iPad work well if you don't want to use the integrated microphone in the iOS device. My Apple earphones worked great in a brief test.

Some users are a bit miffed that they can't work directly with microphones connected to the computer or with Android devices, but at the present time, the iOS dictation API is the best option for the development team to explore integrated speech functions which include program control. That won't work with Chrome speech recognition, for example. As other APIs improve, we can probably expect some new options for memoQ dictation.

Moreover, with the release of iOS 12, I think many older devices (which are cheap on eBay or probably free from friends who don't use them) are now viable tools for Hey memoQ dictation. Update: I found a list of iPhone and iPad devices compatible with iOS 12 here.)

Just for fun, I tested whether Hey memoQ and Dragon NaturallySpeaking interfere with one another. They don't it seems. I switched back and forth from one to the other with no trouble. During the app's beta phase, I did not expect that I would take Hey memoQ as a serious alternative to DNS for English dictation, but with the current set of commands implemented, I can already work with greater comfort than expected, and I may in fact use this free tool quite a bit. And I think my friends working into Portuguese, Russian and other languages not supported by DNS will find Hey memoQ a better option than other dictation solutions I've seen so far.

This is just the beginning. But it's a damned good start really, and I expect very good things ahead from memoQ's development team. And I'm sure that, once again, SDL and others will follow the leader :-)

And last, but not least, here's an update to show how to connect the Hey memoQ app on your iOS device to memoQ 8.7+ on your computer to get started with dictation in translation:

Ferramentas de Tradução - CAT Tools Day at Universidade Nova de Lisboa

The Faculty of Sciences and Humanities held its first "CAT Tools Day" on June 16, 2018 with a diverse program intended to provide a lusophone overview of current best practices in the technologies to support professional translation work. The event offered standard presentation and demonstrations in a university auditorium with parallel software introduction workshops for groups of up to 18 persons in an instructional computer lab in another building.

The day began with morning sessions covering SDL Trados Studio and various aspects of speech recognition.

Dr.  Helena Moniz explains aspects of speech analysis.

I found the presentation by Dr. Helena Moniz from the University of Lisbon faculty to be particularly interesting for its discussion of the many different voice models and how these are applied to speech recognition and text-to-speech synthesis. David Hardisty of FCSH at Universidade Nova also gave a good overview of the state of speech recognition for practical translation work, including his unobtrusive methods for utilizing machine pseudo-translation capabilities in dictated translations.

Parallel introductory workshops for software tools included memoQ 8, SDL Trados Studio 2017 and ABBYY FineReader - two sessions for each.

Attendees learned about ABBYY FineReader, SDL Trados Studio and memoQ in the translation computer lab

The ABBYY FineReader session I attended gave a good overview in Portuguese of basics and good practice, including a discussion of how to avoid common mistakes when converting scanned documents in a number of languages.

The afternoon featured several short, practical presentations by students, discussions by me regarding the upcoming integrated voice input solution for memoQ and the preparation of PDF files for reference, translation, print deadline emergencies and customer relations.

Rúben Mata discusses Discord

The final session of the day was a "tools clinic" - an open Q&A about any aspect of translation technology and workflow challenges. This was a good opportunity to reinforce and elaborate on the many useful concepts and practical approaches shown throughout the day and to share ideas on how to adapt and thrive as a professional in the language services sector today.

Hosts David Hardisty and Marco Neves of FCSH plan to make this an annual event to exchange knowledge on technology and best practices in translation and editing work in discussions between practicing professionals and academics in the lusophone community. So watch for announcements of the next event in 2019!

Some of the topics of this year's conference will be explored in greater depth in three 25-hour courses offered in Portuguese and English this summer at Universidade Nova in Lisbon. On July 9th there will be a thorough course on memoQ Basics and workflows, followed by a Best Practices course on July 19th, covering memoQ and many other aspects of professional work. On September 3rd the university will offer a course on project management skills for language services, including the memoQ Server, project management business tools, file preparation and more. It is apparently also possible to get inexpensive housing at the university to attend these courses, which is quite a good thing given the rapidly rising cost of accommodation in Lisbon. Details on the housing option will be posted on this blog when I can find them.

Survey for Translation Transcription and Dictation

The website with the survey and short explainer video is http://www.sightcat.net
The idea is to build a human transcription service. We just need a few translators per language that want to work with a transcriptionist due to RSI, productivity etc. and we can use that data to build an ASR system for that language. There is also a good chance the ASR system will be accurate for domain-specific terminology and accents as it will be adaptive and use source language context. 

Click on the graphic to go to the survey

memoQ Fest 2018 was, among other things, a good opportunity as always to spend time discussing things with some of the best and most interesting consultants, teachers, creative developers and brainstormers I know in the translation profession. One of these was my friend and colleague, John Moran, whose work on iOmegaT introduced me to the idea that properly designed, translator-controlled (voluntary) data logging could be a great boon to feature research and software development investment decisions. Sort of like SpyGate in translation, except that it isn't.

John and I have been talking, brainstorming and arguing about many aspects of translation technology for years now, dictation (voice recognition, ASR, whatever you want to call it) foremost among the topics. So I was very pleased to see him at the conference in Budapest last week, where he spoke about logging as a research tool in the program and a lot about speech recognition before and after in the breaks, bars, coffee houses and social event venues.

I think that one of the most memorable things about memoQ Fest 2018 was the introduction of the dictation tool currently called hey memoQ, which covers a lot of what John and I have discussed until the wee hours over the past four years or so and which also makes what I believe will be the first commercial use of source text guidance for target text dictation (not to mention switching to source text dictation when editing source texts!). John introduced that to me years ago based on some research that he follows. Fascinating stuff.

One of the things he has been interested in for a while for commercial, academic and ergonomic reasons is support for minor languages. Understandable for a guy who speaks Gaelic (I think) and has quite a lot of Gaelic resources which might contribute to a dictation solution some day. So while I'm excited about the coming memoQ release which will facilitate dictation in a CAT tool in 40 languages (more or less, probably a lot more in the future), John is thinking about smaller, underserved or unserved languages and those who rely on them in their working lives.

That's what his survey is about, and I hope you'll take the time to give him a piece of your mind... uh, share your thoughts I mean :-)

The Great Dictator in Translation.

I have no need for words. memoQ will have that covered in quite a few languages.


This is not your grandfather's memoQ!