no code implementations • 30 Jan 2024 • Yicheng Hsu, Ssuhan Chen, Mingsian R. Bai
The global spatial activity functions are computed from the global spatial coherence functions based on frequency-averaged local spatial activity functions.
no code implementations • 21 Nov 2023 • Yicheng Hsu, Mingsian R. Bai
The results have shown that the proposed BAT system can achieve superior telepresence performance with the desired balance between signal enhancement and ambience preservation, even when the array configurations are unseen in the training phase.
no code implementations • 19 Oct 2023 • HsinYu Chang, Yicheng Hsu, Mingsian R. Bai
Experimental results have shown that the proposed deep beamformer, trained with the linearly weighted scale-invariant source-to-noise ratio (SI-SNR) and ARROW loss functions, achieves superior performance in speech enhancement and speaker localization compared to two baselines.
no code implementations • 18 Apr 2023 • Yicheng Hsu, Mingsian R. Bai
Personal voice activity detection has received increased attention due to the growing popularity of personal mobile devices and smart speakers.
no code implementations • 16 Nov 2022 • Yicheng Hsu, Yonghan Lee, Mingsian R. Bai
Personalized speech enhancement has been a field of active research for suppression of speechlike interferers such as competing speakers or TV dialogues.
no code implementations • 20 Oct 2022 • Yicheng Hsu, Chenghumg Ma, Mingsian R. Bai
Telepresence aims to create an immersive but virtual experience of the audio and visual scene at the far end for users at the near end.
no code implementations • 17 Jul 2022 • Yicheng Hsu, Yonghan Lee, Mingsian R. Bai
Recently, speech enhancement technologies that are based on deep learning have received considerable research attention.
no code implementations • 20 Jun 2022 • Yuan Chen, Yicheng Hsu, Mingsian R. Bai
In this study, a neural beamformer consisting of a beamformer and a novel multi-channel DCCRN is proposed for speech enhancement and source localization.
no code implementations • 10 Dec 2021 • Yicheng Hsu, Yonghan Lee, Mingsian R. Bai
Furthermore, the proposed enhancement system was compared with a baseline system with speaker embeddings and interchannel phase difference.