Speech recognition for interpreters
Numbers and terminology made easy
Do you sometimes struggle to get numbers and terminology right while interpreting?
Wouldnβt it be amazing if your computer could help you with all these pesky bits so you could deliver higher quality interpreting?
Speech recognition for interpreters: Numbers and terminology made easy is the course you've been waiting for!
In over 20 video lessons, we'll walk you through everything you need to know about cutting-edge speech recognition technology.
Course contents
Module 1: Introduction to speech recognition
- How speech recognition works
- Speech recognition for interpreting
- Hey, Siri! An introduction to voice assistants
- Confidentiality and speech recognition
Module 2: Speech recognition for numbers
- Why numbers are so hard
- A first experiment with numbers
- How to set up your computer for speech recognition
- Speech recognition for numbers with InterpretBank
- How well does speech recognition work for numbers in different languages?
Module 3: Speech recognition for terminology
- How to set up InterpretBank to recognize terminology
- How to connect your laptop to the console in the booth
- Test out your own speeches with speech recognition software
- How well does speech recognition work for terms in different languages?
- Speech recognition for named entities
- Why speech recognition sometimes fails
BONUS MODULE: Live automatic transcription and SightConsec - The Next Frontiers?
- Live captioning tools
- How SightConsec works
- A SightConsec demo
This interactive online course is packed with over a dozen hands-on exercises that will walk you through the ins and outs of speech recognition.
Disclaimer: Weβve done our best to compile accurate and reliable information from this rapidly changing field. We research and test to the best of our availability. However, techforword does not accept any liability if something does not work as expected. As you will see in this course, speech recognition is not right for every setting - yet!
Get started now!
Still on the fence?
Check out this demo of speech recognition in action, or enroll in our FREE Getting the right mix: Hassle-free audio for remote interpreting and practice mini-course to see what learning with us is like!
What others are saying about this course

"The βSpeech recognition for Interpretersβ course has truly revolutionized the way I work.
I knew it was possible to use ASR to enhance my performance as a conference interpreter, but there was always some detail missing when I tried it on my own β which led to frustration and I would give up. Here, I felt as if a caring friend was holding my hand, guiding me step-by-step through an overwhelming forest, which soon became an energizing walk in the park.
I took it 6 months ago, and using ASR during assignment has become second nature now.
I never thought I would get there.
Josh and Alex, you rock!"
- Lilia Pino Blouin, Conference Interpreter
Your Instructor
Josh Goldsmith is a UN and EU accredited translator and interpreter working from Spanish, French, Italian and Catalan into English. He splits his time between interpreting, translating, and working as a trainer and researcher focusing on the intersection between interpreting, technology and education. A lover of all things tech, Josh shares tips about technology, translation and interpreting in conferences and workshops, academic articles, the Interpreter's Toolkit column, and on Twitter.
Course Curriculum
-
StartIntro to using speech recognition for preparation (2:09)
-
StartIntro to TurboScribe βπΌ (2:31)
-
StartHow to transcribe a file π§ (2:53)
-
StartMachine translate your transcript π€ (1:33)
-
StartPair up Turboscribe and ChatGPT π―ββοΈ (3:59)
-
StartUse Turboscribe with online videos and audio β―οΈ (0:42)
-
StartWays to use speech recognition for interpreting preparation (3:25)
-
StartDeep dive: How I used Turboscribe + AI to prepare to interpret a keynote π¦Ύ (10:06)
-
StartSemi-automated feedback on your interpreting practice with AI (5:10)
-
StartIntro to live transcription tools (2:16)
-
StartBuilt-in speech recognition on Windows (3:48)
-
StartBuilt-in speech recognition on Mac (3:03)
-
StartBuilt-in speech recognition in Google Chrome (3:04)
-
StartAre Zoom captions enough? (No π) (2:07)
-
StartRecap: Strengths and weaknesses of real-time transcription (2:34)
-
StartIntro to real-time translation (2:28)
-
StartSetting up your browser to capture your audio (2:12)
-
StartGoogle Translate (2:18)
-
StartDeepL Voice (3:10)
-
StartGoogle Chromeβs Live Translate (4:15)
-
StartMaestra Web Captioner (5:58)
-
StartRecap: Strengths and weaknesses of real-time translation tools (1:53)
-
StartAn introduction to CymoNote (3:31)
-
StartWhy I created CymoNote β Reflections from designer Marty Zhu (2:16)
-
StartUsing Cymo Note for terms, numbers and more βΒ a quick demo (0:53)
-
StartSet up Cymo Note languages and speech recognition engines ποΈ (1:37)
-
StartWorking with glossaries on Cymo Note π» (2:00)
-
StartUsing Cymo Note to work with numbers π’ (0:42)
-
StartForce Replace for named entities π€΄π½ (0:25)
-
StartSpeech recognition with running translation (1:39)
-
StartAn Introduction to TerpMate (3:04)
-
StartWhy I created TerpMate: Reflections from founder Bernard Song (2:02)
-
StartSetting up TerpMate (5:26)
-
StartAdd terms to your glossaries in TerpMate (1:01)
-
StartAdd and download glossaries in TerpMate (1:17)
-
StartForce replace with TerpMate (1:43)
-
StartTerpMate's Auto Language Detection Feature (5:56)
-
StartOther nifty features in TerpMate (6:36)
-
StartIntroduction to audio routing (2:51)
-
StartHow to connect your laptop in the booth (1:53)
-
StartHardware for connecting your console in the booth (2:44)
-
StartHow to set up your Windows computer for speech recognition - Routing audio (3:43)
-
StartHow to set up your Mac for speech recognition: Routing audio (3:34)