Search Results - "Hank Liao"

Speaker adaptation of context dependent deep neural networks by Hank Liao

“…There has been little work on examining how deep neural networks may be adapted to speakers for improved speech recognition accuracy. Past work has examined…”
Get full text

A Comparison of End-to-End Models for Long-Form Speech Recognition by Chiu, Chung-Cheng, Han, Wei, Zhang, Yu, Pang, Ruoming, Kishchenko, Sergey, Nguyen, Patrick, Narayanan, Arun, Liao, Hank, Zhang, Shuyuan, Kannan, Anjuli, Prabhavalkar, Rohit, Chen, Zhifeng, Sainath, Tara, Wu, Yonghui

“…End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown…”
Get full text

Reducing the computational complexity for whole word models by Soltau, Hagen, Hank Liao, Hasim Sak

“…In a previous study, we demonstrated the feasibility to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with…”
Get full text

Conformer is All You Need for Visual Speech Recognition by Chang, Oscar, Liao, Hank, Serdyuk, Dmitriy, Shah, Ankit, Siohan, Olivier

“…Visual speech recognition models extract visual features in a hierarchical manner. At the lower level, there is a visual front-end with a limited temporal…”
Get full text

RADMM: Recurrent Adaptive Mixture Model with Applications to Domain Robust Language Modeling by Irie, Kazuki, Kumar, Shankar, Nirschl, Michael, Liao, Hank

“…We present a new architecture and a training strategy for an adaptive mixture of experts with applications to domain robust language modeling. The proposed…”
Get full text

End-to-End Multi-Person Audio/Visual Automatic Speech Recognition by Braga, Otavio, Makino, Takaki, Siohan, Olivier, Liao, Hank

“…Traditionally, audio-visual automatic speech recognition has been studied under the assumption that the speaking face on the visual signal is the face matching…”
Get full text

USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models by Zhao, Guanlong, Wang, Yongqiang, Pelecanos, Jason, Zhang, Yu, Liao, Hank, Huang, Yiling, Lu, Han, Wang, Quan

“…We introduce a multilingual speaker change detection model (USM-SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model…”
Get full text

Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription by Liao, Hank, McDermott, Erik, Senior, Andrew

“…YouTube is a highly visited video sharing website where over one billion people watch six billion hours of video every month. Improving accessibility to these…”
Get full text

Recurrent Neural Network Transducer for Audio-Visual Speech Recognition by Makino, Takaki, Liao, Hank, Assael, Yannis, Shillingford, Brendan, Garcia, Basilio, Braga, Otavio, Siohan, Olivier

“…This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the…”
Get full text

GMM-free DNN acoustic model training by Senior, Andrew, Heigold, Georg, Bacchiani, Michiel, Liao, Hank

“…While deep neural networks (DNNs) have become the dominant acoustic model (AM) for speech recognition systems, they are still dependent on Gaussian mixture…”
Get full text

Exemplar-based large vocabulary speech recognition using k-nearest neighbors by Yanbo Xu, Siohan, Olivier, Simcha, David, Kumar, Sanjiv, Liao, Hank

“…This paper describes a large scale exemplar-based acoustic modeling approach for large vocabulary continuous speech recognition. We construct an index of…”
Get full text

On Robustness to Missing Video for Audiovisual Speech Recognition by Chang, Oscar, Braga, Otavio, Liao, Hank, Serdyuk, Dmitriy, Siohan, Olivier

“…It has been shown that learning audiovisual features can lead to improved speech recognition performance over audio-only features, especially for noisy speech…”
Get full text

Conformers are All You Need for Visual Speech Recognition by Chang, Oscar, Liao, Hank, Serdyuk, Dmitriy, Shah, Ankit, Siohan, Olivier

“…Visual speech recognition models extract visual features in a hierarchical manner. At the lower level, there is a visual front-end with a limited temporal…”
Get full text

Lattice rescoring strategies for long short term memory language models in speech recognition by Kumar, Shankar, Nirschl, Michael, Holtmann-Rice, Daniel, Liao, Hank, Suresh, Ananda Theertha, Yu, Felix

“…Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional…”
Get full text

End-to-End Multi-Person Audio/Visual Automatic Speech Recognition by Braga, Otavio, Makino, Takaki, Siohan, Olivier, Liao, Hank

“…Traditionally, audio-visual automatic speech recognition has been studied under the assumption that the speaking face on the visual signal is the face matching…”
Get full text

DiarizationLM: Speaker Diarization Post-Processing with Large Language Models by Wang, Quan, Huang, Yiling, Zhao, Guanlong, Clark, Evan, Xia, Wei, Liao, Hank

“…In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system…”
Get full text

Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network by Huang, Yiling, Wang, Weiran, Zhao, Guanlong, Liao, Hank, Xia, Wei, Wang, Quan

“…While standard speaker diarization attempts to answer the question "who spoken when", most of relevant applications in reality are more interested in…”
Get full text

USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models by Zhao, Guanlong, Wang, Yongqiang, Pelecanos, Jason, Zhang, Yu, Liao, Hank, Huang, Yiling, Lu, Han, Wang, Quan

“…We introduce a multilingual speaker change detection model (USM-SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model…”
Get full text

Adversarial Training for Multilingual Acoustic Modeling by Hu, Ke, Sak, Hasim, Liao, Hank

“…Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge…”
Get full text

Neural Language Modeling with Visual Features by Anastasopoulos, Antonios, Kumar, Shankar, Liao, Hank

“…Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural…”
Get full text