Enjoyed a great INTERSPEECH 2025 experience! (my first since 2019 at Austria😮‍💨) Kudos to the organizers! Please find our tutorial slides here: voicemos-challenge-2023.github.io/speech-synthes… Also if you work on MOS prediction make sure you check out SHEET! github.com/unilight/sheet

I’m happy to share that our paper, "Discrete Audio Tokens: More Than a Survey!", has been accepted at TMLR. 🎉 📄 Read: arxiv.org/pdf/2506.10274 🔎 Explore our tokenizer database & submit yours: poonehmousavi.github.io/dates-website/…

The 3rd URGENT Challenge just started! 🚀 🎯This time we further expand data diversity and pursue high data quality in the universal SE track. 🎯 I'm also very excited about the new track on SE-oriented SQA. We believe (found) this benefits several areas (SE, TTS, and so on).

SingMOS を使おう！ github.com/South-Twilight…

espnet v.202509 released 🚀 github.com/espnet/espnet/… Includes many updates + fixes for NumPy 2.0 & Python 3.12 (thanks Nelson!). This is the last major update before we shift to the next-gen framework, ESPnet3 Interested in collaborating? Let us know!

Happy to see many familiar faces and be proud of Stella and the world Gaia (hope to have more time playing the game after ICASSP and ICLR submissions 😂

ARECHO has been accepted by #neurips25 as spotlight! Many thanks to all the co-authors for their great effort and support!

Eval for music generation is notoriously ill-defined, but no fear! Presenting MAD, a new metric for music quality with stronger alignment to human preferences. Appearing at ISMIR this week! ⭐: github.com/i-need-sleep/m… 📖: arxiv.org/abs/2503.16669 🔊: mad-metric-83cde1d399d1.herokuapp.com 🧵

Happy to help organize the challenge again!

The SHEET toolkit and the MOS-Bench collection are having MAJOR updates! (1/3) 🗃️ First, MOS-Bench is expanded! Now it has 8 training sets and 17 test sets. A "MOS-Bench at a glance" page is now available -- check out this Google Spreadsheet! docs.google.com/spreadsheets/d…

🎵Music Arena ⚔️ was accepted to the NeurIPS 2025 Creativity Track, and we've released a big update to celebrate! Includes new models from Sonauto AI and ElevenLabs. Also, Music Arena is now available as a 🤗 Hugging Face space and dataset!

Speech isn’t just sound -> it’s how we turn thought into expression. Our new work, Speech-DRAME, measures how well speech AI can act, aligning evaluation with human perception. Paper: arxiv.org/abs/2511.01261 Code: github.com/Anuttacon/spee…

It’s a pleasure to work with Haoran!

This is exactly the reason we worked for ESPnet-Codec, but being really hard to keep tracking as people are fast nowadays. The similar issue happens at most speech tasks from ASR, TTS, to general speech LLM. It's a bit sad time for driving scientific findings 🥲