Yuxuan He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yuxuan He has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Gongping Huang
School of Electronic Information, Wuhan University, Wuhan, China
1 shared publication - Ningning Pan
Southwestern University of Finance and Economics
1 shared publication - Xiaoran Yang
The School of Electronic Information, Wuhan University, Wuhan, China
1 shared publication
Latest Publications
- Open Access
TTMBA: Towards Text To Multiple Sources Binaural Audio Generation
Most existing text-to-audio (TTA) generation methods produce mono outputs, neglecting essential spatial information for immersive auditory experiences. To address this issue, we propose a cascaded method for text-to-multisource binaural audio generation (TTMBA) with both temporal and spatial control. First, a pretrained large language model (LLM) segments the text into a structured format with time and spatial details for each sound event. Next, a pretrained mono audio generation network creates multiple mono audios with varying durations for each event. These mono audios are transformed into binaural audios using a binaural rendering neural network based on spatial data from the LLM. Finally, the binaural audios are arranged by their start times, resulting in multisource binaural audio. Experimental results demonstrate the superiority of the proposed method in terms of both audio generation quality and spatial perceptual accuracy.
Open AccessTTMBA: Towards Text To Multiple Sources Binaural Audio Generation
Most existing text-to-audio (TTA) generation methods produce mono outputs, neglecting essential spatial information for immersive auditory experiences. To address this issue, we propose a cascaded method for text-to-multisource binaural audio generation (TTMBA) with both temporal and spatial control. First, a pretrained large language model (LLM) segments the text into a structured format with time and spatial details for each sound event. Next, a pretrained mono audio generation network creates multiple mono audios with varying durations for each event. These mono audios are transformed into binaural audios using a binaural rendering neural network based on spatial data from the LLM. Finally, the binaural audios are arranged by their start times, resulting in multisource binaural audio. Experimental results demonstrate the superiority of the proposed method in terms of both audio generation quality and spatial perceptual accuracy.