Wangyou Zhang retweeted
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
Wangyou Zhang retweeted
📣 The ICASSP 2027 Speech and Language Processing reviewer nomination form is now open!
Qualified researchers are invited to self-nominate and help shape the ICASSP 2027 technical program.
Review the eligibility requirements and apply here: lnkd.in/etH2wKSv
#ICASSP2027
Wangyou Zhang retweeted
We are looking for a postdoctoral researcher in speech and audio processing, with a possible start in the Fall 2026 semester. If you are interested in working with us, please apply through the following form: forms.gle/gfENMMrRf1nmnTJeA
Wangyou Zhang retweeted
Our multi-speaker ASR paper is now available on CSL😊 We integrate SOTA speech separation (TF-GridNet), self-supervised learning (WavLM), and ASR (Conformer-based joint CTC/AED) models in an end-to-end manner. I really appreciate excellent collaborators!
authors.elsevier.com/a/1l5uB…
Wangyou Zhang retweeted
📢 Introducing VERSA: our new open-source toolkit for speech & audio evaluation!
- 80+ metrics in one unified interface
- Flexible input support
- Distributed evaluation with Slurm
- ESPnet compatible
Check out the details
wavlab.org/activities/2025/v…
github.com/wavlab-speech/ver…
Wangyou Zhang retweeted
🌟 URGENT Challenge @ #Interspeech2025 🌟
Join the Universal, Robust, & Generalizable Speech EnhancemeNT (URGENT) challenge! Explore noisy corpora, tackle diverse speech degradations, and test scalability across 2 tracks (~2.5k/60k hrs).
🚀 Learn more: urgent-challenge.github.io/u…
Wangyou Zhang retweeted
Presentation day!
I am going to present our contribution of Team Hamburgers 🍔 to the URGENT Challenge.
NeurIPS, Saturday Dec 14, 3:45 pm, West Meeting Room 215, 216.
@NeurIPSConf
Wangyou Zhang retweeted
If you are still around in Vancouver for Neurips, tomorrow we will have the URGENT challenge workshop from 1.30 pm.
Come by if you are interested in generalizable speech enhancement (also wind will be up to 70km/h tomorrow and is cozy inside 😉)
Lineup: neurips.cc/virtual/2024/comp…
Wangyou Zhang retweeted
Congratulations, @chenwanch1, for the EMNLP Best Paper Award!!!
I'm super happy!
Wangyou Zhang retweeted
We are thrilled to announce the Interspeech 2025 URGENT Challenge, starting on 11/15!
Join us in building universal speech enhancement models to tackle in-the-wild speech data using large-scale, multilingual data. Details: urgent-challenge.github.io/u…
Wangyou Zhang retweeted
We investigated the scalability of speech enhancement models on different datasets and models (led by @Emrys365 ).
I’ll present this work at #INTERSPEECH2024 Speech Enhancement poster session today at 1:30 pm!
Wangyou Zhang retweeted
I'm excited to announce @WavLab's XEUS - an SSL speech encoder that covers over 4000+ languages!
XEUS is trained on over 1 million hours of speech. It outperforms both MMS 1B and w2v-BERT v2 2.0 on many tasks.
We're releasing the code, checkpoints, and our 4000+ lang. data! 🧵
Wangyou Zhang retweeted
Yet another Mamba paper in #INTERSPEECH2024! We explore Mamba's capability in ASR, TTS, SLU, and SUMM on top of ESPnet. Mamba outperforms S4 in the decoder and demonstrates better length generalization and computational efficiency compared to Transformer.
arxiv.org/abs/2406.16808
Wangyou Zhang retweeted
Excited to co-organize and launch URGENT Challenge as NeurIPS 2024 Competition. The goal of this challenge is to create a “universal speech enhancement” task which goes beyond the usual distortions - additive noise and reverberation. urgent-challenge.github.io/u…
Wangyou Zhang retweeted
🌟 Excited to share our latest work on audio pre-training: EAT - Efficient Audio Transformer! arxiv.org/abs/2401.03497
🚀 Achieving SOTA on AudioSet-2M, AudioSet-20K, ESC-50, and SpeechCommands-v2, EAT boosts pre-training efficiency by 15x compared to previous models.
Wangyou Zhang retweeted
Excited to speak at #ASRU2023 tomorrow (December 20) at 11:30 AM (GMT+8) on "The Journey of Advancements in Speech Foundation Models"! We'll explore the evolution of speech foundation models. Below, please find the slides: drive.google.com/file/d/1ZWf…
Wangyou Zhang retweeted
I'll have a keynote talk at ASRU'23! asru2023.org/motion.asp?site…
See you soon in Taiwan!
Actually, ASRU was the first conference that rejected my first-author paper (in 2003). But 20 years later, I was given the opportunity to be a keynote speaker, haha.
Wangyou Zhang retweeted
📢Our OWSM demo is now available on @huggingface : huggingface.co/spaces/pyf98/…
Many thanks to their support!
OWSM is Open Whisper-style Speech Model from CMU @WavLab lead by @shinjiw_at_cmu . It reproduces Whisper-style training using public data and an open-source toolkit ESPnet.
Wangyou Zhang retweeted
Replying to @shinjiw_at_cmu
@shinjiw_at_cmu @WavLab has released an Open Whisper-style Speech Model (OWSM), perhaps the first attempt in academia to reproduce OpenAI's Whisper from scratch using public data and open-source toolkits. OWSM even supports more translation directions and can be more efficient.
Wangyou Zhang retweeted
We summarize our lab's activities toward speech foundation models at wavlab.org/activities/2023/f….
We have several other ongoing activities, and they are selected papers presented at ASRU.




















