6 citations · 10 across the 23 of their papers we have counts for
26 papers
Multimodal Target Speaker Extraction: Towards Unified Speaker Cues Across Modalities
Xinyuan Qian, Yanghao Zhou, Ziyang Jiang +10
Target Speaker Extraction (TSE) is pivotal in speech communication and human-computer interaction, enabling the isolation of a specific speaker's voice from complex acoustic enviro…
Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction
Lujia Bao, Qian Chen, Luyao Cheng +15
Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements together through…
BiEAR: A Human Auditory-Inspired Adaptive Binaural Front-end for Multi-Speaker Localisation and Distance Estimation
Hanyu Meng, Eliathamby Ambikairajah, Vidhyasaharan Sethu +2
We present BiEAR, a human auditory-inspired adaptive binaural front-end for multi-speaker localisation and distance estimation. Inspired by medial olivocochlear (MOC) feedback in h…
The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models
Xiangyu Zhang, Yuxin Li, Haoyang Zhang +5
The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) --…
Quantizer-Aware Hierarchical Neural Codec Modeling for Speech Deepfake Detection
Jinyang Wu, Zihan Pan, Qiquan Zhang +2
Neural audio codecs discretize speech via residual vector quantization (RVQ), forming a coarse-to-fine hierarchy across quantizers. While codec models have been explored for repres…
Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification
Zexia Fan, Yu Chen, Qiquan Zhang +2
Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance…
Fun-Audio-Chat Technical Report
Tongyi Fun Team, Qian Chen, Luyao Cheng +10
Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatc…
Learning Time-Graph Frequency Representation for Monaural Speech Enhancement
Tingting Wang, Tianrui Wang, Meng Ge +2
The Graph Fourier Transform (GFT) has recently demonstrated promising results in speech enhancement. However, existing GFT-based speech enhancement approaches often employ fixed gr…
Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing
Hanyu Meng, Vidhyasaharan Sethu, Eliathamby Ambikairajah +2
In audio signal processing, learnable front-ends have shown strong performance across diverse tasks by optimizing task-specific representation. However, their parameters remain fix…
SEA-Spoof: Bridging The Gap in Multilingual Audio Deepfake Detection for South-East Asian
Jinyang Wu, Nana Hou, Zihan Pan +3
The rapid growth of the digital economy in South-East Asia (SEA) has amplified the risks of audio deepfakes, yet current datasets cover SEA languages only sparsely, leaving models…
Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
Hexin Liu, Haoyang Zhang, Qiquan Zhang +4
Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that bl…
Benchmarking Gaslighting Attacks Against Speech Large Language Models
Jinyang Wu, Bin Zhu, Xiandong Zou +3
As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input beco…
Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study
Qiquan Zhang, Moran Chen, Zeyang Song +3
Advanced long-context modeling backbone networks, such as Transformer, Conformer, and Mamba, have demonstrated state-of-the-art performance in speech enhancement. However, a system…
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
Haoyang Zhang, Hexin Liu, Xiangyu Zhang +7
The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely e…
Exploring Length Generalization For Transformer-based Speech Enhancement
Qiquan Zhang, Hongxu Zhu, Xinyuan Qian +2
Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for…
Should Audio Front-ends be Adaptive? Comparing Learnable and Adaptive Front-ends
Qiquan Zhang, Buddhi Wickramasinghe, Eliathamby Ambikairajah +2
Hand-crafted features, such as Mel-filterbanks, have traditionally been the choice for many audio processing applications. Recently, there has been a growing interest in learnable…
SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information
Xiangyu Zhang, Hexin Liu, Qiquan Zhang +2
Large Language Models (LLMs) have been increasingly adopted for health-related tasks, yet their performance in depression detection remains limited when relying solely on text inpu…
Time-Graph Frequency Representation with Singular Value Decomposition for Neural Speech Enhancement
Tingting Wang, Tianrui Wang, Meng Ge +3
Time-frequency (T-F) domain methods for monaural speech enhancement have benefited from the success of deep learning. Recently, focus has been put on designing two-stream network m…
Selective State Space Model for Monaural Speech Enhancement
Moran Chen, Qiquan Zhang, Mingjiang Wang +4
Voice user interfaces (VUIs) have facilitated the efficient interactions between humans and machines through spoken commands. Since real-word acoustic scenes are complex, speech en…
SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model
Xinyuan Qian, Jiaran Gao, Yaodan Zhang +4
Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the ma…
Binaural Selective Attention Model for Target Speaker Extraction
Hanyu Meng, Qiquan Zhang, Xiangyu Zhang +2
The remarkable ability of humans to selectively focus on a target speaker in cocktail party scenarios is facilitated by binaural audio processing. In this paper, we present a binau…
An Exploration of Length Generalization in Transformer-Based Speech Enhancement
Qiquan Zhang, Hongxu Zhu, Xinyuan Qian +2
The use of Transformer architectures has facilitated remarkable progress in speech enhancement. Training Transformers using substantially long speech utterances is often infeasible…
Mamba in Speech: Towards an Alternative to Self-Attention
Xiangyu Zhang, Qiquan Zhang, Hexin Liu +6
Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of compu…
An Empirical Study on the Impact of Positional Encoding in Transformer-based Monaural Speech Enhancement
Qiquan Zhang, Meng Ge, Hongxu Zhu +4
Transformer architecture has enabled recent progress in speech enhancement. Since Transformers are position-agostic, positional encoding is the de facto standard component used to…