3.6k citations · 5.2k across the 39 of their papers we have counts for
20 papers · 1 filter
Efficient Adapters for Giant Speech Models
Nanxin Chen, Izhak Shafran, Yu Zhang +4
Large pre-trained speech models are widely used as the de-facto paradigm, especially in scenarios when there is a limited amount of labeled data available. However, finetuning all…
Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data
Alëna Aksënova, Zhehuai Chen, Chung-Cheng Chiu +8
Building inclusive speech recognition systems is a crucial step towards developing technologies that speakers of all language varieties can use. Therefore, ASR systems must work fo…
Cross-attention conformer for context modeling in speech enhancement for ASR
Arun Narayanan, Chung-Cheng Chiu, Tom O'Malley +2
This work introduces \emph{cross-attention conformer}, an attention-based architecture for context modeling in speech enhancement. Given that the context information can often be s…
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
Yu Zhang, Daniel S. Park, Wei Han +23
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a m…
Pushing the Limits of Non-Autoregressive Speech Recognition
Edwin G. Ng, Chung-Cheng Chiu, Yu Zhang +1
We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art result…
Efficient Knowledge Distillation for RNN-Transducer Models
Sankaran Panchapagesan, Daniel S. Park, Chung-Cheng Chiu +3
Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has pl…
A Better and Faster End-to-End Model for Streaming ASR
Bo Li, Anmol Gulati, Jiahui Yu +12
End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by…
Cascaded encoders for unifying streaming and non-streaming ASR
Arun Narayanan, Tara N. Sainath, Ruoming Pang +5
End-to-end (E2E) automatic speech recognition (ASR) models, by now, have shown competitive performance on several benchmarks. These models are structured to either operate in strea…
FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
Jiahui Yu, Chung-Cheng Chiu, Bo Li +8
Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measure…
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
Yu Zhang, James Qin, Daniel S. Park +5
We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabele…
Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition
Wei Li, James Qin, Chung-Cheng Chiu +2
Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-de…
Conformer: Convolution-augmented Transformer for Speech Recognition
Anmol Gulati, James Qin, Chung-Cheng Chiu +8
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (…
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Wei Han, Zhengdong Zhang, Yu Zhang +6
Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper…
Improved Noisy Student Training for Automatic Speech Recognition
Daniel S. Park, Yu Zhang, Ye Jia +5
Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy stude…
RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
Chung-Cheng Chiu, Arun Narayanan, Wei Han +8
In recent years, all-neural end-to-end approaches have obtained state-of-the-art results on several challenging automatic speech recognition (ASR) tasks. However, most existing wor…
SpecAugment on Large Scale Datasets
Daniel S. Park, Yu Zhang, Chung-Cheng Chiu +5
Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhanc…
A comparison of end-to-end models for long-form speech recognition
Chung-Cheng Chiu, Wei Han, Yu Zhang +11
End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance com…
Recognizing long-form speech using streaming end-to-end models
Arun Narayanan, Rohit Prabhavalkar, Chung-Cheng Chiu +3
All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the…
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Daniel S. Park, William Chan, Yu Zhang +4
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coeff…
A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition
Shubham Toshniwal, Anjuli Kannan, Chung-Cheng Chiu +3
Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciati…