b'Yifan Gong'

Streaming Multi-talker Speech Recognition with Joint Speaker Identification

In multi-talker scenarios such as meetings and conversations, speech pro...
04/05/2021 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition

The efficacy of external language model (LM) integration with existing e...
02/02/2021 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Streaming end-to-end multi-talker speech recognition

End-to-end multi-talker speech recognition is an emerging research trend...
11/26/2020 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition

The external language models (LM) integration remains a challenging task...
11/03/2020 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer

Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end...
10/23/2020 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020

This paper describes the Microsoft speaker diarization system for monaur...
10/22/2020 ∙ by Xiong Xiao, et al. ∙ 0 ∙ share

read it
Speaker Separation Using Speaker Inventories and Estimated Speech

We propose speaker separation using speaker inventories and estimated sp...
10/20/2020 ∙ by Peidong Wang, et al. ∙ 0 ∙ share

read it
Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

Because of its streaming nature, recurrent neural network transducer (RN...
07/30/2020 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
Exploring Transformers for Large-Scale Speech Recognition

While recurrent neural networks still largely define state-of-the-art sp...
05/19/2020 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition

Recently, the recurrent neural network transducer (RNN-T) architecture h...
05/01/2020 ∙ by Hu Hu, et al. ∙ 0 ∙ share

read it
L-Vector: Neural Label Embedding for Domain Adaptation

We propose a novel neural label embedding (NLE) scheme for the domain ad...
04/25/2020 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR

Recently, a few novel streaming attention-based sequence-to-sequence (S2...
04/10/2020 ∙ by Hirofumi Inaguma, et al. ∙ 0 ∙ share

read it
High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model

While the community keeps promoting end-to-end models over conventional ...
03/17/2020 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
A Privacy-Preserving DNN Pruning and Mobile Acceleration Framework

To facilitate the deployment of deep neural networks (DNNs) on resource-...
03/13/2020 ∙ by Zheng Zhan, et al. ∙ 0 ∙ share

read it
RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition

Recurrent neural networks (RNNs) based automatic speech recognition has ...
02/19/2020 ∙ by Peiyan Dong, et al. ∙ 0 ∙ share

read it
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency

Structured weight pruning is a representative model compression techniqu...
01/23/2020 ∙ by Zhengang Li, et al. ∙ 0 ∙ share

read it
BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method

Accelerating DNN execution on various resource-limited computing platfor...
01/23/2020 ∙ by Xiaolong Ma, et al. ∙ 7 ∙ share

read it
Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition

Teacher-student (T/S) has shown to be effective for domain adaptation of...
01/06/2020 ∙ by Zhong Meng, et al. ∙ 2 ∙ share

read it
Character-Aware Attention-Based End-to-End Speech Recognition

Predicting words and subword units (WSUs) as the output has shown to be ...
01/06/2020 ∙ by Zhong Meng, et al. ∙ 5 ∙ share

read it
Advances in Online Audio-Visual Meeting Transcription

This paper describes a system that generates speaker-annotated transcrip...
12/10/2019 ∙ by Takuya Yoshioka, et al. ∙ 15 ∙ share

read it
Speaker Adaptation for Attention-Based End-to-End Speech Recognition

We propose three regularization-based speaker adaptation approaches to a...
11/09/2019 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Improving RNN Transducer Modeling for End-to-End Speech Recognition

In the last few years, an emerging trend in automatic speech recognition...
09/26/2019 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
Self-Teaching Networks

We propose self-teaching networks to improve the generalization capacity...
09/09/2019 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Pykaldi2: Yet another speech toolkit based on Kaldi and Pytorch

We introduce PyKaldi2 speech recognition toolkit implemented based on Ka...
07/12/2019 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Encrypted Speech Recognition using Deep Polynomial Networks

The cloud-based speech recognition/API provides developers or enterprise...
05/11/2019 ∙ by Shi-Xiong Zhang, et al. ∙ 0 ∙ share

read it
Adversarial Speaker Adaptation

We propose a novel adversarial speaker adaptation (ASA) scheme, in which...
04/29/2019 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Adversarial Speaker Verification

The use of deep networks to extract embeddings for speaker recognition h...
04/29/2019 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Attentive Adversarial Learning for Domain-Invariant Training

Adversarial domain-invariant training (ADIT) proves to be effective in s...
04/28/2019 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Conditional Teacher-Student Learning

The teacher-student (T/S) learning has been shown to be effective for a ...
04/28/2019 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Speaker Adaptation for End-to-End CTC Models

We propose two approaches for speaker adaptation in end-to-end (E2E) aut...
01/04/2019 ∙ by Ke Li, et al. ∙ 0 ∙ share

read it
Advancing Acoustic-to-Word CTC Model with Attention and Mixed-Units

The acoustic-to-word model based on the Connectionist Temporal Classific...
12/31/2018 ∙ by Amit Das, et al. ∙ 0 ∙ share

read it
Cycle-Consistent Speech Enhancement

Feature mapping using deep neural networks is an effective approach for ...
09/06/2018 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Adversarial Feature-Mapping for Speech Enhancement

Feature-mapping with deep neural networks is commonly used for single-ch...
09/06/2018 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Layer Trajectory LSTM

It is popular to stack LSTM layers to get better modeling power, especia...
08/28/2018 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
Developing Far-Field Speaker System Via Teacher-Student Learning

In this study, we develop the keyword spotting (KWS) and acoustic model ...
04/14/2018 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
Speaker-Invariant Training via Adversarial Learning

We propose a novel adversarial multi-task learning scheme, aiming at act...
04/02/2018 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation

The teacher-student (T/S) learning has been shown effective in unsupervi...
04/02/2018 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Cracking the cocktail party problem by multi-beam deep attractor network

While recent progresses in neural network approaches to single-channel s...
03/29/2018 ∙ by Zhuo Chen, et al. ∙ 0 ∙ share

read it
Advancing Acoustic-to-Word CTC Model

The acoustic-to-word model based on the connectionist temporal classific...
03/15/2018 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
Advancing Connectionist Temporal Classification With Attention Modeling

In this study, we propose advancing all-neural speech recognition by dir...
03/15/2018 ∙ by Amit Das, et al. ∙ 0 ∙ share

read it
Acoustic-To-Word Model Without OOV

Recently, the acoustic-to-word model based on the Connectionist Temporal...
11/28/2017 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition

Unsupervised domain adaptation of speech signal aims at adapting a well-...
11/21/2017 ∙ by Zhong Meng, et al. ∙ 0 ∙ share

read it
Large-Scale Domain Adaptation via Teacher-Student Learning

High accuracy speech recognition requires a large amount of transcribed ...
08/17/2017 ∙ by Jinyu Li, et al. ∙ 0 ∙ share

read it
End-to-End Attention based Text-Dependent Speaker Verification

A new type of End-to-End system for text-dependent speaker verification ...
01/03/2017 ∙ by Shi-Xiong Zhang, et al. ∙ 0 ∙ share

read it

Yifan Gong

Featured Co-authors