Abstract
This paper presents a new computation model for sound stream segregation based on a multi-agent paradigm. Sound streams are thought to play a key role in auditory scene analysis, which provides a general framework for auditory research including voiced speech and music. Each agent is dynamically allocated to a sound stream, and it segregates the stream by focusing on consistent attributes. Agents interact with each other to resolve stream interference. In this paper, we design agents to segregate harmonic streams and a noise stream. The presented system can segregate all the streams from a mixture of a male and a female voiced speech and a background non-harmonic noise.
| Original language | English |
|---|---|
| Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Pages | 2671-2674 |
| Number of pages | 4 |
| Volume | 4 |
| Publication status | Published - 1995 |
| Externally published | Yes |
| Event | Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5) - Detroit, MI, USA Duration: 1995 May 9 → 1995 May 12 |
Other
| Other | Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5) |
|---|---|
| City | Detroit, MI, USA |
| Period | 95/5/9 → 95/5/12 |
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Signal Processing
- Acoustics and Ultrasonics