216 citations · 372 across the 23 of their papers we have counts for
23 papers
Task-Agnostic Structured Pruning of Speech Representation Models
Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang +2
Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks. However, their large memory and strong computatio…
DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model
Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang +1
Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge mod…
Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning
Hao Zhang, Nianwen Si, Yaqi Chen +4
The end-to-end speech translation (E2E-ST) model has gradually become a mainstream paradigm due to its low latency and less error propagation. However, it is non-trivial to train s…
Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based Approach
Anbai Jiang, Wei-Qiang Zhang, Yufeng Deng +2
Automatic detection of machine anomaly remains challenging for machine learning. We believe the capability of generative adversarial network (GAN) suits the need of machine audio a…
Cross-lingual Alzheimer's Disease detection based on paralinguistic and pre-trained features
Xuchu Chen, Yu Pu, Jinpeng Li +1
We present our submission to the ICASSP-SPGC-2023 ADReSS-M Challenge Task, which aims to investigate which acoustic features can be generalized and transferred across languages for…
Expressive Speech-driven Facial Animation with controllable emotions
Yutong Chen, Junhong Zhao, Wei-Qiang Zhang
It is in high demand to generate facial animation with high realism, but it remains a challenging task. Existing approaches of speech-driven facial animation can produce satisfacto…
Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models
Changli Tang, Yujin Wang, Xie Chen +1
Self-supervised learning (SSL) has achieved great success in various areas including speech processing. Recently, it is proven that speech based SSL models are able to extract supe…
LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
Xing Chen, Jie Wang, Xiao-Lei Zhang +2
Although the security of automatic speaker verification (ASV) is seriously threatened by recently emerged adversarial attacks, there have been some countermeasures to alleviate the…
Symmetric Saliency-based Adversarial Attack To Speaker Identification
Jiadi Yao, Xing Chen, Xiao-Lei Zhang +2
Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we pr…
Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models
Haoyu Wang, Wei-Qiang Zhang, Hongbin Suo +1
Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perfo…
Summary on the ISCSLP 2022 Chinese-English Code-Switching ASR Challenge
Shuhao Deng, Chengfei Li, Jinfeng Bai +6
Code-switching automatic speech recognition becomes one of the most challenging and the most valuable scenarios of automatic speech recognition, due to the code-switching phenomeno…
Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition
Yujin Wang, Changli Tang, Ziyang Ma +3
Recent years have witnessed great strides in self-supervised learning (SSL) on the speech processing. The SSL model is normally pre-trained on a great variety of unlabelled data an…
The THUEE System Description for the IARPA OpenASR21 Challenge
Jing Zhao, Haoyu Wang, Jinpeng Li +4
This paper describes the THUEE team's speech recognition system for the IARPA Open Automatic Speech Recognition Challenge (OpenASR21), with further experiment explorations. We achi…
BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Yuting Nie, Junhong Zhao, Wei-Qiang Zhang +1
Language identification is the task of automatically determining the identity of a language conveyed by a spoken segment. It has a profound impact on the multilingual interoperabil…
Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement
Yuzi Yan, Wei-Qiang Zhang, Michael T. Johnson
As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper…
AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style
Yuzi Yan, Xu Tan, Bohan Li +6
While recent text to speech (TTS) models perform very well in synthesizing reading-style (e.g., audiobook) speech, it is still challenging to synthesize spontaneous-style speech (e…
DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling
Lanqing Xue, Kaitao Song, Duocai Wu +5
Rap generation, which aims to produce lyrics and corresponding singing beats, needs to model both rhymes and rhythms. Previous works for rap generation focused on rhyming lyrics bu…
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
Guoguo Chen, Shuzhou Chai, Guanbo Wang +18
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and…
Hierarchical Pooling Structure for Weakly Labeled Sound Event Detection
Ke-Xin He, Yu-Han Shen, Wei-Qiang Zhang
Sound event detection with weakly labeled data is considered as a problem of multi-instance learning. And the choice of pooling function is the key to solving this problem. In this…
SAM-GCNN: A Gated Convolutional Neural Network with Segment-Level Attention Mechanism for Home Activity Monitoring
Yu-Han Shen, Ke-Xin He, Wei-Qiang Zhang
In this paper, we propose a method for home activity monitoring. We demonstrate our model on dataset of Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 Chal…
Learning How to Listen: A Temporal-Frequential Attention Model for Sound Event Detection
Yu-Han Shen, Ke-Xin He, Wei-Qiang Zhang
In this paper, we propose a temporal-frequential attention model for sound event detection (SED). Our network learns how to listen with two attention models: a temporal attention m…
Investigation of Frame Alignments for GMM-based Digit-prompted Speaker Verification
Yi Liu, Liang He, Weiqiang Zhang +2
Frame alignments can be computed by different methods in GMM-based speaker verification. By incorporating a phonetic Gaussian mixture model (PGMM), we are able to compare the perfo…
Tightness of a new and enhanced semidefinite relaxation for MIMO detection
Cheng Lu, Ya-Feng Liu, Wei-Qiang Zhang +1
In this paper, we consider a fundamental problem in modern digital communications known as multi-input multi-output (MIMO) detection, which can be formulated as a complex quadratic…