From the 1 of 6 linked papers with an AI index.
6 papers
OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
Shikhar Bharadwaj, Samuele Cornell, Kwanghee Choi +4
OpenBEATs is an open-source framework that extends the BEATs audio encoder with multi-domain masked-token pretraining, achieving state-of-the-art results on a wide range of audio t…
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…
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…
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…
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 Fréche…