6 citations · 15 across the 15 of their papers we have counts for
3 papers · 1 filter
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
Haoyang Zhang, Hexin Liu, Xiangyu Zhang +7
The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely e…
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors
Shuyue Stella Li, Beining Xu, Xiangyu Zhang +3
In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature…
Generative error correction for code-switching speech recognition using large language models
Chen Chen, Yuchen Hu, Chao-Han Huck Yang +3
Code-switching (CS) speech refers to the phenomenon of mixing two or more languages within the same sentence. Despite the recent advances in automatic speech recognition (ASR), CS-…