6 papers
Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition
Gaopeng Xu, Zhenyu Wang, Zheng Xue +2
The signal ambiguity of whispered speech drives ASR systems toward two opposing failure modes: failing to capture whispered speech or hallucinatory transcription of noise. This pap…
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…
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…
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…
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…
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…