116 citations · 808 across the 43 of their papers we have counts for
18 papers · 1 filter
Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition
Yashesh Gaur, Nick Kibre, Jian Xue +5
Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However, humans prefer a written form output. To bridge this gap, ASR systems usually employ Inve…
Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition
Guoli Ye, Vadim Mazalov, Jinyu Li +1
Hybrid and end-to-end (E2E) systems have their individual advantages, with different error patterns in the speech recognition results. By jointly modeling audio and text, the E2E m…
On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
Liang Lu, Zhong Meng, Naoyuki Kanda +2
Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the…
Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
Hirofumi Inaguma, Yashesh Gaur, Liang Lu +2
Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. Howe…
Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition
Hu Hu, Rui Zhao, Jinyu Li +2
Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of bei…
Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Zhong Meng, Yashesh Gaur, Jinyu Li +1
We propose three regularization-based speaker adaptation approaches to adapt the attention-based encoder-decoder (AED) model with very limited adaptation data from target speakers…
Improving RNN Transducer Modeling for End-to-End Speech Recognition
Jinyu Li, Rui Zhao, Hu Hu +1
In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention E…
PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch
Liang Lu, Xiong Xiao, Zhuo Chen +1
We introduce PyKaldi2 speech recognition toolkit implemented based on Kaldi and PyTorch. While similar toolkits are available built on top of the two, a key feature of PyKaldi2 is…
Speaker Adaptation for End-to-End CTC Models
Ke Li, Jinyu Li, Yong Zhao +2
We propose two approaches for speaker adaptation in end-to-end (E2E) automatic speech recognition systems. One is Kullback-Leibler divergence (KLD) regularization and the other is…
Advancing Acoustic-to-Word CTC Model with Attention and Mixed-Units
Amit Das, Jinyu Li, Guoli Ye +2
The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issue…
Layer Trajectory LSTM
Jinyu Li, Changliang Liu, Yifan Gong
It is popular to stack LSTM layers to get better modeling power, especially when large amount of training data is available. However, an LSTM-RNN with too many vanilla LSTM layers…
Developing Far-Field Speaker System Via Teacher-Student Learning
Jinyu Li, Rui Zhao, Zhuo Chen +4
In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system. Specifically, we use teacher-student (T/S) learning to adapt…
Advancing Acoustic-to-Word CTC Model
Jinyu Li, Guoli Ye, Amit Das +2
The acoustic-to-word model based on the connectionist temporal classification (CTC) criterion was shown as a natural end-to-end (E2E) model directly targeting words as output units…
Advancing Connectionist Temporal Classification With Attention Modeling
Amit Das, Jinyu Li, Rui Zhao +1
In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In…
Acoustic-To-Word Model Without OOV
Jinyu Li, Guoli Ye, Rui Zhao +2
Recently, the acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion was shown as a natural end-to-end model directly targeting words as output u…
Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition
Zhong Meng, Zhuo Chen, Vadim Mazalov +2
Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adver…
Large-Scale Domain Adaptation via Teacher-Student Learning
Jinyu Li, Michael L. Seltzer, Xi Wang +2
High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic mode…
End-to-End Attention based Text-Dependent Speaker Verification
Shi-Xiong Zhang, Zhuo Chen, Yong Zhao +2
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as…