Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud

Importance Weighting Can Help Large Language Models Self-Improve

AttnZero: Efficient Attention Discovery for Vision Transformers

Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search

Can LLMs" Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation

CHATEVAL: Towards better LLM-based evaluators through multi-agent debate

ChatMusician: Understanding and Generating Music Intrinsically with LLM

ComposerX: Multi-Agent Symbolic Music Composition with LLMs

DetKDS: Knowledge Distillation Search for Object Detectors

Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models

FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation

FlashSpeech: Efficient Zero-Shot Speech Synthesis

FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation

Vida: Homeostatic Visual Domain Adapter For Continual Test Time Adaptation

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

Deep Cross-Modal Retrieval Between Spatial Image and Acoustic Speech

CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model

GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios

Generated Therapeutic Music Based on the ISO Principle

LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT

Marble: Music audio representation benchmark for universal evaluation

MoMusic: A Motion-Driven Human-AI Collaborative Music Composition and Performing System

NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis Based on Frequency Modulation

Deep Audio-Visual Beamforming for Speaker Localization

Speech recognition with a hearing-aid processing scheme combining beamforming with mask-informed speech enhancement

Causal System Identification based Compensation for Reverberation-Robust DOA Estimation

Neural Kalman filtering for speech enhancement

Speech Enhancement Based on Modulation-Domain Parametric Multichannel Kalman Filtering

SkipConvNet: Skip convolutional neural network for speech dereverberation using optimally smoothed spectral mapping

Sound event localization and detection based on multiple DOA beamforming and multi-task learning

The JD AI speaker verification system for the FFSVC 2020 challenge

Noise covariance matrix estimation for rotating microphone arrays

Direct-path signal cross-correlation estimation for sound source localization in reverberation

Estimation of the Noise Covariance Matrix for Rotating Sensor Arrays

Modulation-Domain Multichannel Kalman Filtering for Speech Enhancement

Binaural mask-informed speech enhancement for hearing AIDS with head tracking

Modulation-domain parametric multichannel Kalman filtering for speech enhancement

Multichannel Kalman Filtering for Speech Ehnancement

Frequency-domain under-modelled blind system identification based on cross power spectrum and sparsity regularization

Multilingual I-vector based statistical modeling for music genre classification

A novel codebook representation method and encoding strategy for bag-of-words based acoustic event classification

Cross-correlation based under-modelled multichannel blind acoustic system identification with sparsity regularization

Long short-term memory recurrent neural network based segment features for music genre classification

Semi-supervised learning of bottleneck feature for music genre classification

Under-modelled blind system identification for time delay estimation in reverberant environments

Noise Robust Direction of Arrival Estimation for Speech Source with Weighted Bispectrum Spatial Correlation Matrix

Joint optimization of recurrent networks exploiting source auto-regression for source separation

Two-stage multi-target joint learning for monaural speech separation

The analysis of the simplification from the ideal ratio to binary mask in signal-to-noise ratio sense

DOA estimation of speech source in noisy environments with weighted spatial bispectrum correlation matrix

Weighted spatial bispectrum correlation matrix for DOA estimation in the presence of interferences

The optimal ratio time-frequency mask for speech separation in terms of the signal-to-noise ratio

Interference robust DOA estimation of human speech by exploiting historical information and temporal correlation

Direction of arrival estimation based on subband weighting for noisy conditions

Noise covariance matrix estimation for rotating microphone arrays

Article

Direct-path signal cross-correlation estimation for sound source localization in reverberation

Conference paper

Estimation of the Noise Covariance Matrix for Rotating Sensor Arrays

Conference paper

Modulation-Domain Multichannel Kalman Filtering for Speech Enhancement

Article

Binaural mask-informed speech enhancement for hearing AIDS with head tracking

Conference paper

Modulation-domain parametric multichannel Kalman filtering for speech enhancement

Conference paper

Multichannel Kalman Filtering for Speech Ehnancement

Conference paper

Frequency-domain under-modelled blind system identification based on cross power spectrum and sparsity regularization

Conference paper

Multilingual I-vector based statistical modeling for music genre classification

Conference paper

A novel codebook representation method and encoding strategy for bag-of-words based acoustic event classification

Conference paper

Cross-correlation based under-modelled multichannel blind acoustic system identification with sparsity regularization

Conference paper

Long short-term memory recurrent neural network based segment features for music genre classification

Conference paper

Semi-supervised learning of bottleneck feature for music genre classification

Conference paper

Under-modelled blind system identification for time delay estimation in reverberant environments

Conference paper

Noise Robust Direction of Arrival Estimation for Speech Source with Weighted Bispectrum Spatial Correlation Matrix

Article

Joint optimization of recurrent networks exploiting source auto-regression for source separation

Conference paper

Two-stage multi-target joint learning for monaural speech separation

Conference paper

The analysis of the simplification from the ideal ratio to binary mask in signal-to-noise ratio sense

Article

DOA estimation of speech source in noisy environments with weighted spatial bispectrum correlation matrix

Conference paper

Weighted spatial bispectrum correlation matrix for DOA estimation in the presence of interferences

Conference paper

The optimal ratio time-frequency mask for speech separation in terms of the signal-to-noise ratio

Article

Interference robust DOA estimation of human speech by exploiting historical information and temporal correlation

Conference paper

Direction of arrival estimation based on subband weighting for noisy conditions

Conference paper