H
Hank Liao
Researcher at Google
Publications - 34
Citations - 2104
Hank Liao is an academic researcher from Google. The author has contributed to research in topics: Language model & Recurrent neural network. The author has an hindex of 18, co-authored 32 publications receiving 1758 citations. Previous affiliations of Hank Liao include University of Cambridge.
Papers
More filters
Proceedings ArticleDOI
Speaker adaptation of context dependent deep neural networks
TL;DR: This work explores how deep neural networks may be adapted to speakers by re-training the input layer, the output layer or the entire network, and looks at how L2 regularization using weight decay to the speaker independent model improves generalization.
Posted Content
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition
Hagen Soltau,Hank Liao,Hasim Sak +2 more
TL;DR: It is shown that the CTC word models work very well as an end-to-end all-neural speech recognition model without the use of traditional context-dependent sub-word phone units that require a pronunciation lexicon, and without any language model removing the need to decode.
Proceedings ArticleDOI
Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription
TL;DR: Recent improvements to the original YouTube automatic generation of closed captions system are described, in particular the use of owner-uploaded video transcripts to generate additional semi-supervised training data and deep neural networks acoustic models with large state inventories.
Proceedings ArticleDOI
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition
Hagen Soltau,Hank Liao,Hasim Sak +2 more
TL;DR: In this paper, a large vocabulary continuous speech recognition system with whole words as acoustic units is presented. But the model is trained on 125,000 hours of semi-supervised acoustic training data, which enables them to alleviate the data sparsity problem for word models.
Proceedings ArticleDOI
Large Vocabulary Automatic Speech Recognition for Children
Hank Liao,Golan Pundak,Olivier Siohan,Melissa K. Carroll,Noah Coccaro,Qi-Ming Jiang,Tara N. Sainath,Andrew W. Senior,Francoise Beaufays,Michiel Bacchiani +9 more
TL;DR: This paper describes the use of a neural network classifier to identify matched acoustic training data, filtering data for language modeling to reduce the chance of producing offensive results, and compares long short-term memory recurrent networks to convolutional, LSTM, deep neural networks.