Tianshu Qu - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Tianshu Qu

Publications
25
Citations
139
Publications by Year
20092025
Co-Authors:
Show All Co-Authors (26)
Image of author Tianshu Qu

Tianshu Qu

Affiliation

State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology
Peking University
Beijing, China

Publication Topics

Biography

Tianshu Qu received the B.Eng. and M.Eng. degrees from Jilin University of Technology, Changchun, China, in 1993 and 1999, respectively, and the Ph.D. degree from Jilin University, Changchun, China.,After two years as a Postdoctoral Researcher at Peking University, Beijing, China, he became an Assistant Professor in the Key Laboratory of Machine Perception (Ministry of Education), Peking University, in 2004, where he teaches digital signal processing. His principal interests are in acoustic signal processing, auditory modeling, and virtual sound.(Based on document published on 23 June 2009).
Publications
25
Citations
139
Publications by Year
20092025
Co-Authors:
Show All Co-Authors (26)
Author's Published Works

Showing 1-25 of 25 results

  • Sort

Filter Results

Show

Sort By

Results

TA-V2A: Textually Assisted Video-to-Audio Generation

Yuhuan You;Xihong Wu;Tianshu Qu

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2025 | Conference Paper |
As artificial intelligence-generated content (AIGC) continues to evolve, video-to-audio (V2A) generation has emerged as a key area with promising applications in multimedia editing, augmented reality, and automated content creation. While Transformer and Diffusion models have advanced audio generation, a significant challenge persists in extracting precise semantic information from videos, as curr...Show More

TA-V2A: Textually Assisted Video-to-Audio Generation

Yuhuan You;Xihong Wu;Tianshu Qu

Year: 2025 | Conference Paper |

Cross-attention Inspired Selective State Space Models for Target Sound Extraction

Donghang Wu;Yiwen Wang;Xihong Wu;Tianshu Qu

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2025 | Conference Paper |
The Transformer model, particularly its cross-attention module, is widely used for feature fusion in target sound extraction which extracts the signal of interest based on given clues. Despite its effectiveness, this approach suffers from low computational efficiency. Recent advancements in state space models, notably the latest work Mamba, have shown comparable performance to Transformer-based me...Show More

Cross-attention Inspired Selective State Space Models for Target Sound Extraction

Donghang Wu;Yiwen Wang;Xihong Wu;Tianshu Qu

Year: 2025 | Conference Paper |

A Hybrid Deep-Online Learning Based Method for Active Noise Control in Wave Domain

Donghang Wu;Xihong Wu;Tianshu Qu

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2024 | Conference Paper |
The traditional feedback Active Noise Control (ANC) algorithms are built upon linear filters, which leads to reduced performance when dealing with real-world noise. Deep learning-based feedback ANC algorithms have been proposed to overcome this problem. However, methods relying on pre-trained neural networks exhibit performance degradation when encountering noise from unseen scenes in the training...Show More

A Hybrid Deep-Online Learning Based Method for Active Noise Control in Wave Domain

Donghang Wu;Xihong Wu;Tianshu Qu

Year: 2024 | Conference Paper |

Sound Event Localization and Detection Based on Iterative Separation in Embedding Space

Zeyu Yuan;Donghang Wu;Xihong Wu;Tianshu Qu

2023 6th International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2023 | Conference Paper |
Current Sound Event Localization and Detection(SELD) methods mainly adopt the output format from SELDnet that the Direction Of Arrival(DOA) prediction is for each category rather than event, thus these methods cannot handle the simultaneous occurrence of the same type of sound event in different directions. Although track-wise based methods could detect the homogeneous overlap, they are still limi...Show More

Sound Event Localization and Detection Based on Iterative Separation in Embedding Space

Zeyu Yuan;Donghang Wu;Xihong Wu;Tianshu Qu

Year: 2023 | Conference Paper |

A Physical Model-Based Self-Supervised Learning Method for Signal Enhancement Under Reverberant Environment

Shan Gao;Xihong Wu;Tianshu Qu

IEEE/ACM Transactions on Audio, Speech, and Language Processing
Year: 2023 | Volume: 31 | Journal Article |
Cited by: Papers (1)
In a reverberant environment, interferences such as reflections and background noise can degrade the perception of the sound source signal. Although the DNN-based methods have made a tremendous breakthrough in addressing this issue, the performance of these models is highly dependent on the completeness of the training dataset, which will limit its generalization under unknown environments. In thi...Show More

A Physical Model-Based Self-Supervised Learning Method for Signal Enhancement Under Reverberant Environment

Shan Gao;Xihong Wu;Tianshu Qu

Year: 2023 | Volume: 31 | Journal Article |

TT-Net: Dual-Path Transformer Based Sound Field Translation in the Spherical Harmonic Domain

Yiwen Wang;Zijian Lan;Xihong Wu;Tianshu Qu

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2023 | Conference Paper |
Cited by: Papers (1)
In the current method for the sound field translation tasks based on spherical harmonic (SH) analysis, the solution based on the additive theorem usually faces the problem of singular values caused by large matrix condition numbers. The influence of different distances and frequencies of the spherical radial function on the stability of the translation matrix will affect the accuracy of the SH coe...Show More

TT-Net: Dual-Path Transformer Based Sound Field Translation in the Spherical Harmonic Domain

Yiwen Wang;Zijian Lan;Xihong Wu;Tianshu Qu

Year: 2023 | Conference Paper |

A Multi-channel Speech Separation System for Unknown Number of Multiple Speakers

Chao Peng;Yiwen Wang;Xihong Wu;Tianshu Qu

2022 5th International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2022 | Conference Paper |
This paper presents a multi-channel speech separation system for an unknown number of speakers. It can be applied to cases with a different number of speakers using a single model by iterative speech separation based on beam signal. It first determines the spatial directions where speakers are located (Direction of Arrival, DOA), and then the beam signals in each direction are obtained with spectr...Show More

A Multi-channel Speech Separation System for Unknown Number of Multiple Speakers

Chao Peng;Yiwen Wang;Xihong Wu;Tianshu Qu

Year: 2022 | Conference Paper |

Sparse DNN Model for Frequency Expanding of Higher Order Ambisonics Encoding Process

Shan Gao;Jing Lin;Xihong Wu;Tianshu Qu

IEEE/ACM Transactions on Audio, Speech, and Language Processing
Year: 2022 | Volume: 30 | Journal Article |
Cited by: Papers (10)
The performance of higherorder Ambisonics (HOA) signals obtained using spherical harmonics decomposition method is disturbed by two primary sources of errors, the noise pollution in low-frequency band and the spatial aliasing in high-frequency band. Inspired by the HOA signals upscale method, which is performed using the sparse character of the sound field, this paper propose a sound field decompo...Show More

Sparse DNN Model for Frequency Expanding of Higher Order Ambisonics Encoding Process

Shan Gao;Jing Lin;Xihong Wu;Tianshu Qu

Year: 2022 | Volume: 30 | Journal Article |

Early Reflections Based Speech Enhancement

Jianfei Chen;Xihong Wu;Tianshu Qu

2021 4th International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2021 | Conference Paper |
Reverberation is generally considered harmful to speech intelligibility and will cause degradation to speech related tasks. However, we propose a framework taking advantage of the early reflections (ER), which is part of reverberation, to tackle the speech enhancement problem in this work. First, a fully convolutional neural network (FCNN) is introduced to estimate the direction of arrivals (DOA) ...Show More

Early Reflections Based Speech Enhancement

Jianfei Chen;Xihong Wu;Tianshu Qu

Year: 2021 | Conference Paper |

Partially Matching Projection Decoding Method Evaluation Under Different Playback Conditions

Zhongshu Ge;Liang Li;Tianshu Qu

IEEE/ACM Transactions on Audio, Speech, and Language Processing
Year: 2021 | Volume: 29 | Journal Article |
Cited by: Papers (1)
The Ambisonic technique has been widely used in fields such as sound-field reproduction, sound source localization, and acoustic noise control. In this paper, a recently proposed Ambisonic decoding method, the partially matching projection method (PMPD), was described in detail and extended for more practical use with near-field sources and reverberant playback environments. Several experiments we...Show More

Partially Matching Projection Decoding Method Evaluation Under Different Playback Conditions

Zhongshu Ge;Liang Li;Tianshu Qu

Year: 2021 | Volume: 29 | Journal Article |

Anti Spatial Aliasing HOA Encoding Method based on Aliasing Projection Matrix

Jing Lin;Xihong Wu;Tianshu Qu

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2020 | Conference Paper |
Cited by: Papers (2)
Higher order Ambisonics (HOA) is a 3D sound decomposition and reproduction technology that represent 3D sound fields based on a series of spherical harmonic functions. However, practical application of HOA technology is limited by narrow available bandwidth, low-frequency noise pollution and high-frequency spatial aliasing. Inspired by the sparse recovery method, anti-spatial aliasing HOA encoding...Show More

Anti Spatial Aliasing HOA Encoding Method based on Aliasing Projection Matrix

Jing Lin;Xihong Wu;Tianshu Qu

Year: 2020 | Conference Paper |

A Time-domain Unsupervised Learning Based Sound Source Localization Method

Yankun Huang;Xihong Wu;Tianshu Qu

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2020 | Conference Paper |
Cited by: Papers (6)
In recent years, deep neural networks have been applied in many fields. In this paper, a time-domain unsupervised learning based sound source localization method is proposed, where auto-encoder neural networks are adopted so that some operation like time-delay compensation can be removed and there is no need to prepare training data with precise alignment labels. In order to improve its performanc...Show More

A Time-domain Unsupervised Learning Based Sound Source Localization Method

Yankun Huang;Xihong Wu;Tianshu Qu

Year: 2020 | Conference Paper |

Individual Distance-Dependent HRTFS Modeling Through A Few Anthropometric Measurements

Mengfan Zhang;Xihong Wu;Tianshu Qu

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2020 | Conference Paper |
Cited by: Papers (5)
The lack of data is a major problem in individual HRTF modeling. There are many HRTF databases, but each database only has limited HRTFs with different characteristics, such as distance-dependent HRTFs or individual HRTFs. How to effectively model HRTFs through several different databases is an important task. In this paper, a method for predicting individual distance-dependent HRTFs using a few a...Show More

Individual Distance-Dependent HRTFS Modeling Through A Few Anthropometric Measurements

Mengfan Zhang;Xihong Wu;Tianshu Qu

Year: 2020 | Conference Paper |

Modeling of Individual HRTFs Based on Spatial Principal Component Analysis

Mengfan Zhang;Zhongshu Ge;Tiejun Liu;Xihong Wu;Tianshu Qu

IEEE/ACM Transactions on Audio, Speech, and Language Processing
Year: 2020 | Volume: 28 | Journal Article |
Cited by: Papers (26)
Head-related transfer function (HRTF) plays an important role in the construction of 3D auditory display. This article presents an individual HRTF modeling method using deep neural networks based on spatial principal component analysis. The HRTFs are represented by a small set of spatial principal components combined with frequency and individual-dependent weights. By estimating the spatial princi...Show More

Modeling of Individual HRTFs Based on Spatial Principal Component Analysis

Mengfan Zhang;Zhongshu Ge;Tiejun Liu;Xihong Wu;Tianshu Qu

Year: 2020 | Volume: 28 | Journal Article |

Beamforming and Deep Models Integrated Multi-talker Speech Separation

Chao Peng;Xihong Wu;Tianshu Qu

2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP)
Year: 2019 | Conference Paper |
Recently, although the traditionally proposed Permutation Invariant Training (PIT) has attracted much attention, it performs poorly on datasets of unknown number of speakers. In this paper, we propose an approach based on beamforming and deep models (BDM) to solve the problem mentioned above. BDM firstly estimates the number of speakers by sound source localization algorithm and then enhances the ...Show More

Beamforming and Deep Models Integrated Multi-talker Speech Separation

Chao Peng;Xihong Wu;Tianshu Qu

Year: 2019 | Conference Paper |

Eigen Beam Based Sound Source Localization Algorithms Evaluation on a Non-Spherical Microphone Array

Shan Gao;Rui Liu;Xihong Wu;Tianshu Qu

2019 IEEE 2nd International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2019 | Conference Paper |
Cited by: Papers (1)
The traditional eigen beam based localization algorithms are usually not employed on the non-spherical microphone array, for which the eigen beam is hard to be obtained. In this paper, the transfer functions are introduced to calculated the eigen beam on the non-spherical microphone array. Based on it, three localization algorithms including the eigen beam based intensity vector, eigen beam based ...Show More

Eigen Beam Based Sound Source Localization Algorithms Evaluation on a Non-Spherical Microphone Array

Shan Gao;Rui Liu;Xihong Wu;Tianshu Qu

Year: 2019 | Conference Paper |

A Time-domain End-to-End Method for Sound Source Localization Using Multi-Task Learning

Yankun Huang;Xihong Wu;Tianshu Qu

2019 IEEE 2nd International Conference on Information Communication and Signal Processing (ICICSP)
Year: 2019 | Conference Paper |
Cited by: Papers (2)
In recent years, many researches focus on sound source localization based on neural networks, which is an appealing but difficult problem. In this paper, a novel time-domain end-to-end method for sound source localization is proposed, where the model is trained by two strategies with both cross entropy loss and mean square error loss. Based on the idea of multi-task learning, CNN is used as the sh...Show More

A Time-domain End-to-End Method for Sound Source Localization Using Multi-Task Learning

Yankun Huang;Xihong Wu;Tianshu Qu

Year: 2019 | Conference Paper |

Improvements to the Matching Projection Decoding Method for Ambisonic System with Irregular Loudspeaker Layouts

Zhongshu Ge;Xihong Wu;Tianshu Qu

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2019 | Conference Paper |
Cited by: Papers (4)
The Ambisonic technique has been widely used for sound field recording and reproduction recently. However, the basic Ambisonic decoding method will break down when the playback loudspeakers distribute unevenly. Various methods have been proposed to solve this problem. This paper introduces several improvements to a recently proposed Ambisonic decoding method, the matching projection method, for un...Show More

Improvements to the Matching Projection Decoding Method for Ambisonic System with Irregular Loudspeaker Layouts

Zhongshu Ge;Xihong Wu;Tianshu Qu

Year: 2019 | Conference Paper |

Distance-dependent Modeling of Head-related Transfer Functions

Mengfan Zhang;Yue Qiao;Xihong Wu;Tianshu Qu

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2019 | Conference Paper |
Cited by: Papers (4)
In this paper, a method for modeling distance dependent head-related transfer functions is presented. The HRTFs are first decomposed by spatial principal component analysis. Using deep neural networks, we model the spatial principal component weights of different distances. Then we realize the prediction of HRTFs in arbitrary spatial distances. The objective and subjective experiments are conducte...Show More

Distance-dependent Modeling of Head-related Transfer Functions

Mengfan Zhang;Yue Qiao;Xihong Wu;Tianshu Qu

Year: 2019 | Conference Paper |

A Modified Frequency Weighted MUSIC Algorithm for Multiple Sound Sources Localization

Shan Gao;Yankun Huang;Tao Zhang;Xihong Wu;Tianshu Qu

2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)
Year: 2018 | Conference Paper |
Cited by: Papers (5)
The traditional weighted MUSIC algorithm is usually implemented based on a sparsity assumption named W-Disjoint Orthogonality (WDO) when the number of sound sources is unknown, which may not be suitable in many scenarios. In this paper, a modified weighted MUSIC algorithm is proposed to improve the localization performance in multiple sound sources. Instead of using the maximum eigenvalue as the w...Show More

A Modified Frequency Weighted MUSIC Algorithm for Multiple Sound Sources Localization

Shan Gao;Yankun Huang;Tao Zhang;Xihong Wu;Tianshu Qu

Year: 2018 | Conference Paper |

Matching Projection Decoding Method for Ambisonics System

Tianshu Qu;Zhichao Huang;Yue Qiao;Xihong Wu

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2018 | Conference Paper |
Cited by: Papers (4)
The basic Ambisonics decoding method will break down when the playback loudspeakers distribute unevenly. This paper proposes a modified Ambisonics method, the matching projection decoding method, for solving this problem. The matching projection decoding method is a kind of the greedy algorithm. It firstly calculates the projection value of the object Ambisonics signal over each Ambisonics signal ...Show More

Matching Projection Decoding Method for Ambisonics System

Tianshu Qu;Zhichao Huang;Yue Qiao;Xihong Wu

Year: 2018 | Conference Paper |

An environment adaptive loudspeaker calibration method for Ambisonics decoding system

Zhichao Huang;Shan Gao;Tianshu Qu;Liang Li;Xihong Wu

2016 International Conference on Audio, Language and Image Processing (ICALIP)
Year: 2016 | Conference Paper |
Cited by: Papers (1)
In the Ambisonics decoding system, the non-evenly placement of loudspeakers, the non-identical characters of each sound playing channel and the reverberation of the listening room will destroy the spatial perception of the virtual sound. In this paper, an environment adaptive loudspeaker calibration method is proposed for accurately reproducing the sound field by using the Ambisonics system. The t...Show More

An environment adaptive loudspeaker calibration method for Ambisonics decoding system

Zhichao Huang;Shan Gao;Tianshu Qu;Liang Li;Xihong Wu

Year: 2016 | Conference Paper |

An accurate decorrelation method for parametric stereo coding

Tianshu Qu;Qingbo Huang;Yichao Huang;Liang Li;Xihong Wu

2016 International Conference on Audio, Language and Image Processing (ICALIP)
Year: 2016 | Conference Paper |
Decorrelator is a module to restore the specific correlation properties between stereo signals in parametric stereo audio decoder, which is vital to keep the spatial information of the stereo signals. Generally, the existing decorrelators are prone to have a comb-filter effect which results in an undesirable “metallic” sound and produce temporal smearing such as pre- and post-echoes artefacts. Thi...Show More

An accurate decorrelation method for parametric stereo coding

Tianshu Qu;Qingbo Huang;Yichao Huang;Liang Li;Xihong Wu

Year: 2016 | Conference Paper |

Audio lossless coding/decoding method using basis pursuit algorithm

Wenxin He;Tianshu Qu

2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2013 | Conference Paper |
Cited by: Papers (3)
Basis pursuit algorithm is one of the most popular methods of sparse coding. The goal of the algorithm is to represent signal using as few coefficients as possible, which is suitable for acoustic signal compression. This paper presents a lossless coding/decoding method using the basis pursuit algorithm. In this method, wavelet packets bases were used to compose the dictionary because of their natu...Show More

Audio lossless coding/decoding method using basis pursuit algorithm

Wenxin He;Tianshu Qu

Year: 2013 | Conference Paper |

Distance-Dependent Head-Related Transfer Functions Measured With High Spatial Resolution Using a Spark Gap

Tianshu Qu;Zheng Xiao;Mei Gong;Ying Huang;Xiaodong Li;Xihong Wu

IEEE Transactions on Audio, Speech, and Language Processing
Year: 2009 | Volume: 17, Issue: 6 | Journal Article |
A measurement of head-related transfer functions (HRTFs) with high spatial resolution was carried out in this study. HRTF measurement is difficult in the proximal region because of the lack of an appropriate acoustic point source. In this paper, a modified spark gap was used as the acoustic sound source. Our evaluation experiments showed that the spark gap was more like an acoustic point source th...Show More

Distance-Dependent Head-Related Transfer Functions Measured With High Spatial Resolution Using a Spark Gap

Tianshu Qu;Zheng Xiao;Mei Gong;Ying Huang;Xiaodong Li;Xihong Wu

Year: 2009 | Volume: 17, Issue: 6 | Journal Article |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.