2 papers
eess.AS2025
Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantization
Jian You, Xiangfeng Li, Erwan Zerhouni
Conventional automatic speech recognition (ASR) models typically produce outputs as normalized texts lacking punctuation and capitalization, necessitating post-processing models to…
cs.CL2024
A light-weight and efficient punctuation and word casing prediction model for on-device streaming ASR
Jian You, Xiangfeng Li
Punctuation and word casing prediction are necessary for automatic speech recognition (ASR). With the popularity of on-device end-to-end streaming ASR systems, the on-device punctu…