5 papers
Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
Jinchuan Tian, Haoran Wang, Bo-Hao Su +14
Current audio foundation models typically rely on rigid, task-specific supervision (e.g., speech recognition), addressing isolated factors of audio rather than the whole. In contra…
CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech
Brian Yan, Qingzheng Wang, Matthew Wiesner +9
We present CS-YODAS, a Creative Commons-licensed dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching (CS), or the alternation between l…
Fish Audio S2 Technical Report
Shijia Liao, Yuxuan Wang, Songting Liu +11
We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-l…
Geolocation-Aware Robust Spoken Language Identification
Qingzheng Wang, Hye-jin Shim, Jiancheng Sun +1
While Self-supervised Learning (SSL) has significantly improved Spoken Language Identification (LID), existing models often struggle to consistently classify dialects and accents o…
Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC
Qingzheng Wang, Jiancheng Sun, Yifan Peng +1
Multilingual speech processing with self-supervised or supervised pre-trained Speech Foundation Models (SFM) has achieved strong performance on tasks like Language Identification (…