7 papers · 1 filter
AcousticAgent: A Floorplan-Centric Simulation Platform for Distributed Multi-Room Speech Processing
Zhiqi Ai, Han Cheng, Shiyi Mu +2
Existing acoustic simulation tools either generate room impulse responses (RIRs) efficiently in parameterized rooms or rely on preconstructed three-dimensional scenes, making it di…
Bridge, Distill, Refine: High-Fidelity One-Step Generation for Multi-Bandwidth Speech Extension
Zhiqi Ai, Xu Shen, Mou Wang +2
Speech bandwidth extension (BWE) aims to recover missing spectral content from band-limited speech. However, most generative BWE methods are designed for fixed input bandwidths and…
Stabilizing Short Duration Speaker Verification through Neural Re-scoring with Hybrid Enrollment
Zhiqi Ai, Han Cheng, Shiyi Mu +3
Short-duration speaker verification (SDSV) is crucial for personalized keyword spotting, where test utterances are typically shorter than three seconds. Limited speech duration res…
Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation
Zhiqi Ai, Han Cheng, Shiyi Mu +3
User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable…
Enhancing Open-Set Speaker Identification through Rapid Tuning with Speaker Reciprocal Points and Negative Sample
Zhiyong Chen, Zhiqi Ai, Xinnuo Li +1
This paper introduces a novel framework for open-set speaker identification in household environments, playing a crucial role in facilitating seamless human-computer interactions.…
StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis
Zhiyong Chen, Xinnuo Li, Zhiqi Ai +1
We introduce StyleFusion-TTS, a prompt and/or audio referenced, style and speaker-controllable, zero-shot text-to-speech (TTS) synthesis system designed to enhance the editability…
MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting
Zhiqi Ai, Zhiyong Chen, Shugong Xu
In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that fo…