8 papers
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…
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet
Anyu Ying, Natarajan Balaji Shankar, Chyi-Jiunn Lin +7
Despite advancements in ASR, child speech recognition remains challenging due to acoustic variability and limited annotated data. While fine-tuning adult ASR models on child speech…
OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
Shikhar Bharadwaj, Samuele Cornell, Kwanghee Choi +4
Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a sin…
Uni-VERSA: Versatile Speech Assessment with a Unified Network
Jiatong Shi, Hye-Jin Shim, Shinji Watanabe
Subjective listening tests remain the golden standard for speech quality assessment, but are costly, variable, and difficult to scale. In contrast, existing objective metrics, such…
Aligning Text-to-Music Evaluation with Human Preferences
Yichen Huang, Zachary Novack, Koichi Saito +5
Despite significant recent advances in generative acoustic text-to-music (TTM) modeling, robust evaluation of these models lags behind, relying in particular on the popular Fréchet…
VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music
Jiatong Shi, Hye-jin Shim, Jinchuan Tian +14
In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for various speech, audio, and music signals. The toolkit features a Pythonic interface wit…
Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
Hye-jin Shim, Md Sahidullah, Jee-weon Jung +2
Current trends in audio anti-spoofing detection research strive to improve models' ability to generalize across unseen attacks by learning to identify a variety of spoofing artifac…
To what extent can ASV systems naturally defend against spoofing attacks?
Jee-weon Jung, Xin Wang, Nicholas Evans +6
The current automatic speaker verification (ASV) task involves making binary decisions on two types of trials: target and non-target. However, emerging advancements in speech gener…