Liyong Guo

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

Binbin Zhang, Di Wu, Zhuoyuan Yao et al. · arXiv (Cornell University) · 2020 · 46 citations · Full text

Engineering, Machine Learning, Spoken Language Processing +20

Reducing noisy annotations for depression estimation from facial images

Lang He, Prayag Tiwari, Chonghua Lv et al. · Neural Networks · 2022 · 40 citations · Full text

Pruned RNN-T for fast, memory-efficient ASR training

Fangjun Kuang, Liyong Guo, Wei Kang et al. · Interspeech 2022 · 2022 · 40 citations

Natural Language Processing, Memory-efficient Asr Training, Engineering +14

Zipformer: A faster and better encoder for automatic speech recognition

Zengwei Yao, Liyong Guo, Xiaoyu Yang et al. · arXiv (Cornell University) · 2023 · 28 citations · Full text

Engineering, Machine Learning, Global Dependencies +19

Libriheavy: A 50,000 Hours ASR Corpus with Punctuation Casing and Context

Wei Kang, Xiaoyu Yang, Zengwei Yao et al. · 2024 · 23 citations

Syntactic Parsing, Engineering, Machine Learning +28