Presented Papers

Low-Resource Self-Supervised Learning with SSL-Enhanced TTS

Po-chun Hsu (National Taiwan University); Ali Elkahky (Apple); Wei-Ning Hsu (Meta); Yossi Adi (Facebook AI Research ); Tu Anh Nguyen (Meta); Jade Copet (Meta); Emmanuel Dupoux (Meta); Hung-yi Lee (National Taiwan University); Abdelrahman Mohamed (Rembrand Inc)

SELF-SUPERVISED PRETRAINING FOR ROBUST SPEECH EVALUATION

Huayun Zhang (ASTAR); Jeremy H. M. Wong (Institute for Infocomm Research); Geyu Lin (Agency of Science and Technology Research); Naaman Tan (NUS); Nancy Chen (Institute for Infocomm Research)

Noise robust distillation of self-supervised speech models via correlation metrics

Fabian Alejandro Ritter-Gutierrez (Nanyang Technological University); Kuan-Po Huang (National Taiwan University); Dianwen Ng (Alibaba Group / Nanyang Technological University); Jeremy H. M. Wong (Institute for Infocomm Research); Hung-yi Lee (National Taiwan University); Eng Siong Chng (Nanyang Technological University); Nancy Chen (Institute for Infocomm Research)

Non-Intrusive Speech Intelligibility Prediction for Hearing Impaired Individuals using Self-Supervised Speech Representations

George L Close (University of Sheffield); Thomas Hain (University of Sheffield); Stefan Goetze (University of Sheffield)

An Exploration of In-Context Learning for Speech Language Model

Kai-Wei Chang (National Taiwan University); Ming-Hao Hsu (National Taiwan University); Shang-Wen Li (FAIR); Hung-yi Lee (National Taiwan University)

LongHuBERT: Evaluating the Importance of Attention in Self-supervised Speech Encoders

William Chen (Carnegie Mellon University); Takatomo Kano (NTT Corporation); Atsunori Ogawa (NTT Corporation); Marc Delcroix (NTT); Shinji Watanabe (Carnegie Mellon University)

A Parameter-Efficient Learning Baseline for Acoustic Modeling under Frozen Pre-trained Settings

Zih-Ching Chen (National Taiwan University); SHIH-HENG WANG (National Taiwan University); Tzu-Han Lin (National Taiwan University); How-Shing Wang (National Taiwan University); Sabato M Siniscalchi (Kore University of Enna); Hung-yi Lee (National Taiwan University)

SLUE-PERB: A Spoken Language Understanding Performance Benchmark and Toolkit

Siddhant Arora (Carnegie Mellon University); Roshan S Sharma (Carnegie Mellon University); Ankita Pasad (Toyota Technological Institute at Chicago); Hira Dhamyal (Carnegie Mellon University); William Chen (Carnegie Mellon University); Suwon Shon (ASAPP); Hung-yi Lee (National Taiwan University); Karen Livescu (TTI-Chicago); Shinji Watanabe (Carnegie Mellon University)