TTMBA: Towards Text To Multiple Sources Binaural Audio Generation
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model2025
- AudioLDM 2: Learning Holistic Audio Generation With Self-Supervised PretrainingIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
- Diffsound: Discrete Diffusion Model for Text-to-Sound GenerationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- Headphone simulation of free-field listening. I: Stimulus synthesisThe Journal of the Acoustical Society of America, 1989
- Pinna reflections as cues for localizationThe Journal of the Acoustical Society of America, 1974
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951