184 citations · 557 across the 54 of their papers we have counts for
7 papers · 1 filter
An analysis of incorporating an external language model into a sequence-to-sequence model
Anjuli Kannan, Yonghui Wu, Patrick Nguyen +3
Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model comp…
No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models
Tara N. Sainath, Rohit Prabhavalkar, Shankar Kumar +9
For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-…
Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models
Rohit Prabhavalkar, Tara N. Sainath, Yonghui Wu +4
Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds t…
Improving the Performance of Online Neural Transducer Models
Tara N. Sainath, Chung-Cheng Chiu, Rohit Prabhavalkar +4
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-t…
State-of-the-art Speech Recognition With Sequence-to-Sequence Models
Chung-Cheng Chiu, Tara N. Sainath, Yonghui Wu +11
Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic…
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
Chris Donahue, Bo Li, Rohit Prabhavalkar
We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR…
Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Models
Yanzhang He, Rohit Prabhavalkar, Kanishka Rao +3
We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly…