---
title: "Residue-Driven Architecture for Computational Auditory Scene Analysis"
authors:
  - "Tomohiro Nakatani"
  - "Hiroshi G. Okuno"
  - "Takeshi Kawabata"
doi: ""
url: "https://ijcai.org/proceedings/1995/22"
pdf: "https://ijcai.org/proceedings/1995/0022.pdf"
venue: "Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence"
year: 1995
pages: "165-173"
track: "Action and Perception"
keywords:
---

# Residue-Driven Architecture for Computational Auditory Scene Analysis

Tomohiro Nakatani, Hiroshi G. Okuno, Takeshi Kawabata

*Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence*, pages 165-173.

## Abstract

The Residue-Driven Architecture presented her e is a model of auditory stream segregation from input sounds. A subsystem to extr a ct auditory str e ams by using some sound attributes is called an agency and the design of each agency is based on the residue-driven architecture . This architecture consists of three kinds of agents: an event-detector, a tracergenerator, and tracers. The event-detector calculates a residue by subtracting the predicted input from the actual input. When a residue exceeds a threshold value, tracer-generator generates a tracerthat extracts an auditory stream from the residue and returns a predicted input of the next time frame to the event-detector. This approach improves the performance of segregation and the resulting system can segregate a woman's voiced stream, a man's voiced stream, and a noise stream from a mixture of these sounds. Binaural segregation is also designed by the architecture.