6 papers
Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement
Ziling Huang, Haixin Guan, Yanhua Long
Conventional speech enhancement (SE) aims to improve speech perception and intelligibility by suppressing noise without requiring enrollment speech as reference, whereas personaliz…
Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios
Yiming Yang, Guangyong Wang, Haixin Guan +1
Target speech extraction (TSE) typically relies on pre-recorded high-quality enrollment speech, which disrupts user experience and limits feasibility in spontaneous interaction. In…
Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition
Yuxiang Mei, Delai Qiu, Shengping Liu +2
Speech Large Language Models (Speech-LLMs) have emerged as a powerful approach for automatic speech recognition (ASR) by aligning speech encoders with large language models. Howeve…
Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios
Ziling Huang, Junnan Wu, Lichun Fan +4
Target speech extraction (TSE) has achieved strong performance in relatively simple conditions such as one-speaker-plus-noise and two-speaker mixtures, but its performance remains…
Noisy Disentanglement with Tri-stage Training for Noise-Robust Speech Recognition
Shuangyuan Chen, Shuang Wei, Dongxing Xu +1
To enhance the performance of end-to-end (E2E) speech recognition systems in noisy or low signal-to-noise ratio (SNR) conditions, this paper introduces NoisyD-CT, a novel tri-stage…
SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation
Ziling Huang, Haixin Guan, Haoran Wei +1
Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding t…