WAVLab | @CarnegieMellon retweeted
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…
WAVLab | @CarnegieMellon 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
WAVLab is at #Interspeech2026 in Sydney 🇦🇺
Our papers cover speech recognition, spoken LLMs, speech synthesis, speech quality, and multilingual data. Plus the new ESPnet3 toolkit!
Here's where to find us, Sep 28 to Oct 1 🧵
Thu, Oct 1
15:20 · Room C2.5
Endpoint Anticipation for Low-Latency Spoken Dialogue
arxiv.org/abs/2606.13450
Thu, Oct 1
14:00-16:00 · Poster, Gallery p7
Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens
arxiv.org/abs/2607.26350
Thu, Oct 1
09:00-11:00 · Room C3.6 (special session)
Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling
arxiv.org/abs/2604.00489
10:40 · Room C3.3
Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis
arxiv.org/abs/2606.22811
Wed, Sep 30
17:50 · Room C2.1
URGENT-MOS: Unified Multi-Metric and Preference Learning for Robust Speech Quality Assessment
arxiv.org/abs/2601.18438
Wed, Sep 30
17:10 · Darling Harbour Theatre
Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings
arxiv.org/abs/2606.17542
Wed, Sep 30
16:50 · Room C2.1
ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling
arxiv.org/abs/2606.10233
Wed, Sep 30
15:00 · Room C3.3
ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era
arxiv.org/abs/2606.21854
15:40 · Room C2.6
Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption
arxiv.org/abs/2606.21227
Wed, Sep 30
14:00-16:00 · Poster, Gallery p6
YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech
arxiv.org/abs/2609.29448
Wed, Sep 30
09:00-11:00 · Poster, Gallery p6
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
arxiv.org/abs/2607.02119
Wed, Sep 30
09:00 · Room C2.2
Comparative Reasoning: Making an Audio Language Model Better at Comparing Emotions
arxiv.org/abs/2606.24082
Tue, Sep 29
17:30 · Room C2.2
An Empirical Recipe for Universal Phone Recognition
arxiv.org/abs/2603.29042
Mon, Sep 28
14:30-16:30 · Poster, Gallery p4
Online Predictive Coding for Dual-Mode Self-Supervised Speech Models
arxiv.org/abs/2606.21268
Mon, Sep 28
12:40 · Room C3.4
Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics
arxiv.org/abs/2603.22709
Mon, Sep 28
11:40 · Darling Harbour Theatre
Which Data Matter? Embedding-Based Data Selection for Speech Recognition
arxiv.org/abs/2603.05819
12:00 · Room C3.4
Speaker-Aware Hypothesis Clustering and Merging for Target-Speaker-free and Target-Speaker Multi-Talker ASR
Mon, Sep 28
11:00 · Room C3.4
Mind the Gap: Impact of Synthetic Conversational Data on Multi-Talker ASR and Speaker Diarization
arxiv.org/abs/2605.15442
11:20 · Room C3.4
Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning
arxiv.org/abs/2606.18134