Usable Speech Assignment for Speaker Identification under Co-Channel Situation

TL;DR

This paper introduces a model-based speaker assignment method to organize usable speech segments into a single speaker stream for improved speaker identification in co-channel speech, demonstrating significant performance gains.

Contribution

The paper proposes a novel speaker assignment system using posterior probability and exhaustive search to enhance SID in co-channel scenarios.

Findings

Significant improvement in speaker identification accuracy.

Effective organization of speech segments into single speaker streams.

Validated on TIMIT database with promising results.

Abstract

Usable speech criteria are proposed to extract minimally corrupted speech for speaker identification (SID) in co-channel speech. In co-channel speech, either speaker can randomly appear as the stronger speaker or the weaker one at a time. Hence, the extracted usable segments are separated in time and need to be organized into speaker streams for SID. In this paper, we focus to organize extracted usable speech segment into a single stream for the same speaker by speaker assignment system. For this, we develop model-based speaker assignment method based on posterior probability and exhaustive search algorithm. Evaluation of this method is performed on TIMIT database. The system is evaluated on co-channel speech and results show a significant improvement.