Qiang Huang

is this you? claim profile

0 followers
National University of Singapore ∙ University of Surrey ∙ The University of Sheffield ∙ Jilin University

T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model

Identifying multiple speakers without knowing where a speaker's voice is...
10/29/2020 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Improving Audio Anomalies Recognition Using Temporal Convolutional Attention Network

Anomalous audio in speech recordings is often caused by speaker voice di...
10/21/2020 ∙ by Qiang Huang, et al. ∙ 0 ∙ share

read it
Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models

Many applications of speech technology require more and more audio data....
05/16/2020 ∙ by Qiang Huang, et al. ∙ 0 ∙ share

read it
Speaker Re-identification with Speaker Dependent Speech Enhancement

While the use of deep neural networks has significantly boosted speaker ...
05/15/2020 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification

Identifying multiple speakers without knowing where a speaker's voice is...
05/15/2020 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Locality-Sensitive Hashing Scheme based on Longest Circular Co-Substring

Locality-Sensitive Hashing (LSH) is one of the most popular methods for ...
04/11/2020 ∙ by Yifan Lei, et al. ∙ 0 ∙ share

read it
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks

Graph structured data has wide applicability in various domains such as ...
01/17/2020 ∙ by Qiang Huang, et al. ∙ 22 ∙ share

read it
Robust Speaker Recognition Using Speech Enhancement And Attention Model

In this paper, a novel architecture for speaker recognition is proposed ...
01/14/2020 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems

Question Answering (QA) systems are used to provide proper responses to ...
11/18/2019 ∙ by Qiang Huang, et al. ∙ 0 ∙ share

read it
H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model

In this paper, a hierarchical attention network to generate utterance-le...
10/17/2019 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Contextual Joint Factor Acoustic Embeddings

Embedding acoustic information into fixed length representations is of i...
10/16/2019 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Improving Robustness In Speaker Identification Using A Two-Stage Attention Model

In this paper a novel framework to tackle speaker recognition using a tw...
09/24/2019 ∙ by Yanpei Shi, et al. ∙ 0 ∙ share

read it
Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging

Environmental audio tagging is a newly proposed task to predict the pres...
02/24/2017 ∙ by Yong Xu, et al. ∙ 0 ∙ share

read it
Hierarchical learning for DNN-based acoustic scene classification

In this paper, we present a deep neural network (DNN)-based acoustic sce...
07/13/2016 ∙ by Yong Xu, et al. ∙ 0 ∙ share

read it
Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging

Environmental audio tagging aims to predict only the presence or absence...
07/13/2016 ∙ by Yong Xu, et al. ∙ 0 ∙ share

read it
Fully DNN-based Multi-label regression for audio tagging

Acoustic event detection for content analysis in most cases relies on lo...
06/24/2016 ∙ by Yong Xu, et al. ∙ 0 ∙ share

read it

Qiang Huang

Featured Co-authors

Yong Xu

Makoto Yamada

Mohan Kankanhalli

Yuan Tian

Qiuqiang Kong

Mark D. Plumbley

Wenwu Wang

Yi Chang

Dawei Yin

Thomas Hain

Siddharth Sigtia

T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model

Improving Audio Anomalies Recognition Using Temporal Convolutional Attention Network

Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models

Speaker Re-identification with Speaker Dependent Speech Enhancement

Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification

Locality-Sensitive Hashing Scheme based on Longest Circular Co-Substring

GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks

Robust Speaker Recognition Using Speech Enhancement And Attention Model

Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems

H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model

Contextual Joint Factor Acoustic Embeddings

Improving Robustness In Speaker Identification Using A Two-Stage Attention Model

Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging

Hierarchical learning for DNN-based acoustic scene classification

Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging

Fully DNN-based Multi-label regression for audio tagging