←
WAVLab | @CarnegieMellon354 posts
WAVLab | @CarnegieMellon avatar

WAVLab | @CarnegieMellon

@WavLab

Shinji Watanabe's Audio and Voice Lab | WAVLab @LTIatCMU @SCSatCMU | Speech Recognition, Speech Enhancement, Spoken Language Understanding, and more.

◷ Joined August 2021▧ 19 Photos and videos
Shinji Watanabe avatar
⟳ WAVLab | @CarnegieMellon retweeted
Shinji Watanabe@shinjiw_at_cmu·Oct 22

The CHiME-3 background noise recordings are now openly available on Zenodo under CC BY 4.0 🙂 Six-channel tablet array, 16 kHz, four real environments: bus, café, pedestrian area, street. Reuse and redistribution OK, including commercial use Thanks, Jon! doi.org/10.5281/zenodo.23571…

Post attachment
WAVLab | @CarnegieMellon avatar
WAVLab | @CarnegieMellon@WavLab·Nov 5

Great to see old friends in Pittsburgh this week! 😊 Our former postdocs Jee-weon and Hye-jin were in town. Jee-weon is teaching Speech Recognition this month, and Hye-jin gave a guest lecture in Speech Generation. We also caught up with Kai-Wei at his Speech Lunch talk today!

Post attachmentPost attachmentPost attachment
WAVLab | @CarnegieMellon avatar
WAVLab | @CarnegieMellon@WavLab·Nov 2

🚀 ESPnet v.202611 is here! Highlights: • Audio quality assessment (AQA) • Bagpiper CLI & MCP support • New espnet run command • SDPA across speech encoders • F5-TTS & ESPnet3 updates 124 merged PRs from 22 contributors. Thanks to everyone! github.com/espnet/espnet/rel…

Shinji Watanabe avatar
⟳ WAVLab | @CarnegieMellon retweeted
Shinji Watanabe@shinjiw_at_cmu·Oct 3

My Google Scholar h-index just reached 100! 🙂 My first paper was in 1999, and behind these 100 are students and collaborators in academia and industry, plus the open-source community and challenges. This number is really yours. Thank you all! 🙏 scholar.google.com/citations…

Post attachment
William Chen avatar
⟳ WAVLab | @CarnegieMellon retweeted
William Chen@chenwanch1·Sep 28

Who wants more speech training data? YODAS v3 is now available @huggingface It’s 1.1M hours - the biggest audio dataset ever. And the first at this scale with stereo audio at 48kHz, with timestamped transcripts and translations. 100+ langs hf.co/blog/espnet/yodasv3 CC-BY-3.0

WAVLab | @CarnegieMellon avatar
WAVLab | @CarnegieMellon@WavLab·Sep 27

Next up, join our afternoon tutorial: Sun, Sep 27 · 13:30-17:00 · Room C3.3 Conversational Speech Recognition and Analysis - Progress, Challenges, and Emerging Opportunities with Speech Language Models