Discover the Future of Speech Technology!

🤖 Speech Tech Summer School: 🤖 robots, 👾 video games, 🗯 voice cloning ... and more!

🗓 May 14-17
📍 Campus Fryslân - University of Groningen @universityofgroningen , the Netherlands

⏰ Few spots left!

https://www.rug.nl/education/summer-winter-schools/speech-technology/?lang=en

Please share w interested students of all backgrounds!
#voicetechnology #speechtechnology #speechtech, #summerschool #speechrecognition #voiceai

Discover the Future of Speech Technology!

🤖 Speech Tech Summer School: robots, video games, voice cloning ... and more!
🗓 May 14-17
📍 Campus Fryslân - University of Groningen, the Netherlands

From robots 🤖 to video games 👾 to speech recognition 🗯, our hands-on summer school will feature workshops plus, speakers from Google, Respeecher, and more.

⏰ Space is limited!
https://www.rug.nl/education/summer-winter-schools/speech-technology/?lang=en

#voicetechnology #speechtechnology #speechtech, #summerschool #speechrecognition #voiceai

A week ago today I was speaking at the 1st Dutch Speech Tech Day in Hilversum. Focusing on what the University of Groningen #VoiceTech team was working on and introducing the new MSc Voice Tech. Plus, promoted the upcoming #SpeechTech #SummerSchool

Congrats to Leminh Nguyen from the MSc Voice Technology who was nominated for the prestigious Ben Feringa Impact award because of his groundbreaking work on Luxembourgish Speech Recognition! 💻🗯️ Freely available, #OpenAccess #speechTech for #Luxembourgish 👏🇱🇺 well done!!

https://www.rug.nl/news/2023/01/nominees-for-the-ben-feringa-impact-award-to-be-announced

Our MSc Voice Tech grad Leminh Nguyen presented his poster at the 2022 IEEE Spoken Language Technology workshop: "improving #Luxembourgish speech recognition with cross-lingual speech representations" #SpeechRecognition #SpeechTech

The IEEE Workshop on “Self-supervision in Audio, Speech, and Beyond” will be held jointly with ICASSP.

📍 Greece 🇬🇷
🗓️ June 4 -- 9
📨 Submissions accepted until Feb 24th.

Accepted papers will appear in the official IEEE ICASSP proceedings and IEEE Xplore.

ℹ️ More info:

https://sites.google.com/view/icassp-sasb-2023/descriptionons

#cfp #audio #SpeechTech #VoiceTech

@nickfisherau Nice. Did you publish any details about your alignment code?
For post-edit - maybe #Praat is easier for #speechtech?
I recently did phone alignment tool as a gift to Czech #phonetics and minimizing dependencies (and install hassle), I finally went without anything like Kaldi, using just very basic #Pytorch for NN AM training and then alignment. I guess going zero-up was really easier than decomposing some big thing like Whisper.
https://github.com/vaclavhanzl/prak

I still need to manually check (and occasionally correct) the alignments though.

I wrote a couple of Python scripts/extension for Audacity that loads up the audio/labels so you can manually drag the handles to adjust the alignments. Works pretty well!

I know there are various web interfaces for this but seems you need to use them for your entire pipeline (ingest/labelling/export/indexing/etc) or not at all.

#asr #speechtech #speechrecognition #machinelearning

I still need to manually check (and occasionally correct) the alignments though.

I wrote a couple of Python scripts/extension for Audacity that loads up the audio/labels so you can manually drag the handles to adjust the alignments. Works pretty well!

I know there are various web interfaces for this but seems you need to use them for your entire pipeline (ingest/labelling/export/indexing/etc) or not at all.

#asr #speechtech #speechrecognition #machinelearning

RT @martijnwieling
We have 2 @FacultyofArtsUG @GroNlp vacancies for tenured (!) Assist. Profs in #CompLing/#SpeechTech. If you are interested in applying #SpeechTech to minority languages, contact me, as more research time (up to 70%) may then be possible: https://www.rug.nl/about-ug/work-with-us/job-opportunities/?details=00347-02S0009PQP. RT=nice!

Hi everyone we are the Phonetics Lab at Lancaster University! We'll be tooting about fun phonetics stuff as well as news from our lab and collaborators. @LAEL #introduction #phonetics #linguistics #phonology #labphon #sociophonetics #articulation #forensicphonetics #speechtech #bilingualism #ultrasound #EMA

Hi everyone we are the Phonetics Lab at Lancaster University! We'll be tooting about fun phonetics stuff as well as news from our lab and collaborators.
#introduction #phonetics #linguistics #phonology #labphon #sociophonetics #articulation #forensicphonetics #speechtech #bilingualism #ultrasound #EMA

💡 Interesting read on how one of the biggest commercial players out there plans to use Mozilla Open Voice data to make speech AI more inclusive and open to more language.

💬 Sounds idealistic, but Open Voice datasets are created by unpaid volunteers who donate hours and hours of their speech. Not sure whether I feel comfortable with that, tbh.

💭 Thoughts?

https://venturebeat.com/ai/nvidia-enters-the-speech-ai-race-joining-meta-and-google/

#ethicalAI #transparentai #voice #speech #voicetech #speechtech #speechAI

We'll dig deeper into OpenAI Whisper (https://openai.com/blog/whisper/) this weekend. I'll announce a DateTime for the YT live stream here later.

Note: It's not a presentation but a #StudyWithMe session. You can also join in on the task/Livestream via audio/video through Google Meet.

YT Link: http://youtube.com/@datadrivenbabe

#Data #VoiceTech #NLP #SpeechTech #AI #ML #MLOps

How much do you know about the sub-field already?

We'll dig deeper into OpenAI Whisper (https://openai.com/blog/whisper/) this weekend. I'll announce a DateTime for the YT live stream here later.

Note: It's not a presentation but a #StudyWithMe session. You can also join in on the task/Livestream via audio/video through Google Meet.

YT Link: http://youtube.com/@datadrivenbabe

#Data #VoiceTech #NLP #SpeechTech #AI #ML #MLOps

How much do you know about the sub-field already?

Maybe an interesting opportunity for students working in #speechtech : Internship (6 months) at NAVER LABS Europe to contribute to the development of a “single TTS model with the ability to control speaker identity, emotions, prosodic focus, etc” https://europe.naverlabs.com/job/fine-grained-multi-faceted-control-of-prosodic-features-for-tts-systems-internship/

Tune in for Dr Shekhar Nayak’s lecture at LITHME 2nd int’l conference — stream it now! Zero research speech processing #speechtech https://m3.jyu.fi/jyumv/ohjelmat/hum/kivi/lithme/2nd-international-conference-language-in-the-human-machine-era/stream-2-b348-puro

Today at #sigul2022 (#lrec2022) our team will present research on phoneme mapping and source-language selection in transfer learning for TTS in under-resourced languages. Full paper here http://www.lrec-conf.org/proceedings/lrec2022/workshops/SIGUL/pdf/2022.sigul-1.3.pdf #speechtech #text2speech #speechsynthesis

Interesting #speechtech job: Software Engineer (Full Stack) - Common Voice #mozilla — more info: https://www.linkedin.com/jobs/view/3074447615/?eBP=JOB_SEARCH_ORGANIC&recommendedFlavor=IN_NETWORK&refId=%2F1dFsv%2FpaQHUrb0skdAupg%3D%3D&trackingId=il%2B74RRs6ajFwTzwM1afew%3D%3D&trk=flagship3_search_srp_jobs