Peizhuo Liu — accepted AI-conference papers

2025

Adaptive Decoding for Efficient Automatic Speech Recognition

Xiangnan Ma, Peizhuo Liu, Yuhao Zhang, Kaiqi Kou, Chenghao Gao, Tong Xiao +1

ICASSP 2025accepted

The latency and computation demand of End-to-end (E2E) automatic speech recognition (ASR) models hinder their deployment on lightweight devices. Despite there are many methods proposed for efficiency, the computational burden of the output layer with a large vocabulary is still a major challenge for…

Cited by 0 Source ↗Scholar ↗

2025

Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation

Yuhao Zhang, Xiangnan Ma, Kaiqi Kou, Peizhuo Liu, Weiqiao Shan, Benyou Wang +4

ACL 2025finding

The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM), and 2) learning alignment of difference languages in long se…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗