Search Results for author: Jiangyan Yi

Found 22 papers, 0 papers with code

Half-Truth: A Partially Fake Audio Detection Dataset

no code implementations8 Apr 2021 Jiangyan Yi, Ye Bai, JianHua Tao, Zhengkun Tian, Chenglong Wang, Tao Wang, Ruibo Fu

Diverse promising datasets have been designed to hold back the development of fake audio detection, such as ASVspoof databases.

Speech Synthesis

FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization

no code implementations7 Apr 2021 Zhengkun Tian, Jiangyan Yi, Ye Bai, JianHua Tao, Shuai Zhang, Zhengqi Wen

It takes a lot of computation and time to predict the blank tokens, but only the non-blank tokens will appear in the final output sequence.

Speech Recognition

TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition

no code implementations4 Apr 2021 Zhengkun Tian, Jiangyan Yi, JianHua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen, Xuefei Liu

To address these two problems, we propose a new model named the two-step non-autoregressive transformer(TSNAT), which improves the performance and accelerating the convergence of the NAR model by learning prior knowledge from a parameters-sharing AR model.

Speech Recognition

Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning

no code implementations11 Nov 2020 Cunhang Fan, Bin Liu, JianHua Tao, Jiangyan Yi, Zhengqi Wen, Leichao Song

This paper proposes a deep time delay neural network (TDNN) for speech enhancement with full data learning.

Speech Enhancement

Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition

no code implementations9 Nov 2020 Cunhang Fan, Jiangyan Yi, JianHua Tao, Zhengkun Tian, Bin Liu, Zhengqi Wen

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR).

automatic-speech-recognition End-To-End Speech Recognition +2

One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition

no code implementations28 Oct 2020 Zhengkun Tian, Jiangyan Yi, Ye Bai, JianHua Tao, Shuai Zhang, Zhengqi Wen

Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model.

Language Modelling Speech Recognition

Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognition

no code implementations28 Oct 2020 Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Ye Bai, JianHua Tao, Zhengqi Wen

In this paper, we propose a decoupled transformer model to use monolingual paired data and unpaired text data to alleviate the problem of code-switching data shortage.

automatic-speech-recognition Speech Recognition

Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition

no code implementations16 May 2020 Zhengkun Tian, Jiangyan Yi, Jian-Hua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen

To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence.

End-To-End Speech Recognition Machine Translation +1

Simultaneous Denoising and Dereverberation Using Deep Embedding Features

no code implementations6 Apr 2020 Cunhang Fan, Jian-Hua Tao, Bin Liu, Jiangyan Yi, Zhengqi Wen

In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC).

Deep Clustering Denoising +3

Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method

no code implementations17 Mar 2020 Cunhang Fan, Jian-Hua Tao, Bin Liu, Jiangyan Yi, Zhengqi Wen, Xuefei Liu

Secondly, to pay more attention to the outputs of the pre-separation stage, an attention module is applied to acquire deep attention fusion features, which are extracted by computing the similarity between the mixture and the pre-separated speech.

Deep Attention Speech Quality +1

Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition

no code implementations19 Feb 2020 Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Jian-Hua Tao, Ye Bai

Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition.

Language Identification Speech Recognition

Synchronous Transformers for End-to-End Speech Recognition

no code implementations6 Dec 2019 Zhengkun Tian, Jiangyan Yi, Ye Bai, Jian-Hua Tao, Shuai Zhang, Zhengqi Wen

Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately.

End-To-End Speech Recognition Speech Recognition

Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data

no code implementations4 Dec 2019 Ye Bai, Jiangyan Yi, Jian-Hua Tao, Zhengqi Wen, Zhengkun Tian, Shuai Zhang

To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence.

End-To-End Speech Recognition Language Modelling +1

Self-Attention Transducers for End-to-End Speech Recognition

no code implementations28 Sep 2019 Zhengkun Tian, Jiangyan Yi, Jian-Hua Tao, Ye Bai, Zhengqi Wen

Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance.

End-To-End Speech Recognition Speech Recognition

Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features

no code implementations23 Jul 2019 Cunhang Fan, Bin Liu, Jian-Hua Tao, Jiangyan Yi, Zhengqi Wen

Firstly, a DC network is trained to extract deep embedding features, which contain each source's information and have an advantage in discriminating each target speakers.

Deep Clustering Speech Separation

Cannot find the paper you are looking for? You can Submit a new open access paper.