9 papers
LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression
Chengwei Liu, Shaofei Xue, Haoyin Yan +2
We propose a lightweight multi-path alignment network (LMPAN) for on-device joint acoustic echo cancellation (AEC) and noise suppression (NS) in full-duplex spoken dialogue systems…
Discrete Token Modeling for Multi-Stem Music Source Separation with Language Models
Pengbo Lyu, Xiangyu Zhao, Chengwei Liu +4
We propose a generative framework for multi-track music source separation (MSS) that reformulates the task as conditional discrete token generation. Unlike conventional approaches…
A Hybrid Discriminative and Generative System for Universal Speech Enhancement
Yinghao Liu, Chengwei Liu, Xiaotao Liang +3
Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes…
Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
YuXiang Kong, JunFeng Hou, Jian Tang +3
Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hot…
QuarkAudio Technical Report
Chengwei Liu, Haoyin Yan, Shaofei Xue +5
Many existing audio processing and generation models rely on task-specific architectures, resulting in fragmented development efforts and limited extensibility. It is therefore pro…
Synaspot: A Lightweight, Streaming Multi-modal Framework for Keyword Spotting with Audio-Text Synergy
Kewei Li, Yinan Zhong, Xiaotao Liang +2
Open-vocabulary keyword spotting (KWS) in continuous speech streams holds significant practical value across a wide range of real-world applications. While increasing attention has…
UniTok-Audio: A Unified Audio Generation Framework via Generative Modeling on Discrete Codec Tokens
Chengwei Liu, Haoyin Yan, Shaofei Xue +5
Generative modeling has recently achieved remarkable success across text, image, and audio domains, demonstrating powerful capabilities for unified representation learning. However…
UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement
Haoyin Yan, Chengwei Liu, Shaofei Xue +4
Neural audio codecs have largely promoted the application of language models (LMs) for speech applications. However, the effectiveness of autoregressive LM-based models in unifying…
OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation
Qijun Gan, Ruizi Yang, Jianke Zhu +2
Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animati…