67 citations · 211 across the 44 of their papers we have counts for
21 papers · 1 filter
The Impact of Silence on Speech Anti-Spoofing
Yuxiang Zhang, Zhuo Li, Jingze Lu +3
The current speech anti-spoofing countermeasures (CMs) show excellent performance on specific datasets. However, removing the silence of test speech through Voice Activity Detectio…
Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
Han Zhu, Dongji Gao, Gaofeng Cheng +3
When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, p…
Online Hybrid CTC/Attention End-to-End Automatic Speech Recognition Architecture
Haoran Miao, Gaofeng Cheng, Pengyuan Zhang +1
Recently, there has been increasing progress in end-to-end automatic speech recognition (ASR) architecture, which transcribes speech to text without any pre-trained alignments. One…
Multi-dimensional frequency dynamic convolution with confident mean teacher for sound event detection
Shengchang Xiao, Xueshuai Zhang, Pengyuan Zhang
Recently, convolutional neural networks (CNNs) have been widely used in sound event detection (SED). However, traditional convolution is deficient in learning time-frequency domain…
Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion
Yuxiang Zhang, Jingze Lu, Xingming Wang +5
This paper describes the deepfake audio detection system submitted to the Audio Deep Synthesis Detection (ADD) Challenge Track 3.2 and gives an analysis of score fusion. The propos…
SASV Based on Pre-trained ASV System and Integrated Scoring Module
Yuxiang Zhang, Zhuo Li, Wenchao Wang +1
Based on the assumption that there is a correlation between anti-spoofing and speaker verification, a Total-Divide-Total integrated Spoofing-Aware Speaker Verification (SASV) syste…
Interrelate Training and Searching: A Unified Online Clustering Framework for Speaker Diarization
Yifan Chen, Yifan Guo, Qingxuan Li +3
For online speaker diarization, samples arrive incrementally, and the overall distribution of the samples is invisible. Moreover, in most existing clustering-based methods, the tra…
Decoupled Federated Learning for ASR with Non-IID Data
Han Zhu, Jindong Wang, Gaofeng Cheng +2
Automatic speech recognition (ASR) with federated learning (FL) makes it possible to leverage data from multiple clients without compromising privacy. The quality of FL-based ASR c…
Boosting Cross-Domain Speech Recognition with Self-Supervision
Han Zhu, Gaofeng Cheng, Jindong Wang +3
The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domai…
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
Keqi Deng, Zehui Yang, Shinji Watanabe +3
While Transformers have achieved promising results in end-to-end (E2E) automatic speech recognition (ASR), their autoregressive (AR) structure becomes a bottleneck for speeding up…
Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR
Han Zhu, Li Wang, Jindong Wang +3
Self-supervised pre-training could effectively improve the performance of low-resource automatic speech recognition (ASR). However, existing self-supervised pre-training are task-a…
Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search
Yukun Liu, Ta Li, Pengyuan Zhang +1
Recently neural architecture search(NAS) has been successfully used in image classification, natural language processing, and automatic speech recognition(ASR) tasks for finding th…
Beam-Guided TasNet: An Iterative Speech Separation Framework with Multi-Channel Output
Hangting Chen, Yang Yi, Dang Feng +1
Time-domain audio separation network (TasNet) has achieved remarkable performance in blind source separation (BSS). Classic multi-channel speech processing framework employs signal…
Domain Adaptation Using Class Similarity for Robust Speech Recognition
Han Zhu, Jiangjiang Zhao, Yuling Ren +2
When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained sou…
Multi-Accent Adaptation based on Gate Mechanism
Han Zhu, Li Wang, Pengyuan Zhang +1
When only a limited amount of accented speech data is available, to promote multi-accent speech recognition performance, the conventional approach is accent-specific adaptation, wh…
Exploring the time-domain deep attractor network with two-stream architectures in a reverberant environment
Hangting Chen, Pengyuan Zhang
Deep attractor networks (DANs) perform speech separation with discriminative embeddings and speaker attractors. Compared with methods based on the permutation invariant training (P…
ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
Hangting Chen, Zuozhen Liu, Zongming Liu +1
In acoustic scene classification (ASC), acoustic features play a crucial role in the extraction of scene information, which can be stored over different time scales. Moreover, the…
Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture
Haoran Miao, Gaofeng Cheng, Changfeng Gao +2
Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online spe…
CN-CELEB: a challenging Chinese speaker recognition dataset
Yue Fan, Jiawen Kang, Lantian Li +7
Recently, researchers set an ambitious goal of conducting speaker recognition in unconstrained conditions where the variations on ambient, channel and emotion could be arbitrary. H…
Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model
Hangting Chen, Pengyuan Zhang, Yonghong Yan
In this letter, we present a novel multi-talker minimum variance distortionless response (MVDR) beamforming as the front-end of an automatic speech recognition (ASR) system in a di…
Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling
Hangting Chen, Zuozhen Liu, Zongming Liu +2
This technical report describes the IOA team's submission for TASK1A of DCASE2019 challenge. Our acoustic scene classification (ASC) system adopts a data augmentation scheme employ…