2 papers
cs.SD2025
Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
Zhennan Lin, Kaixun Huang, Wei Ren +2
Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as…
eess.AS2024
Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
Hongfei Xue, Wei Ren, Xuelong Geng +6
Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including…