3 papers
cs.SD2024
Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction
Zhaoxi Mu, Xinyu Yang, Sining Sun +1
Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certa…
cs.SD2024
Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study
Peikun Chen, Sining Sun, Changhao Shan +2
Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (A…
cs.CL2024
Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognition
Wenjing Zhu, Sining Sun, Changhao Shan +2
Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output…