Sorry, you need to enable JavaScript to visit this website.

WASPAA 2019 POSTER: MULTIPLE HYPOTHESIS TRACKING FOR OVERLAPPING SPEAKER SEGMENTATION

Primary tabs

Citation Author(s):
Aidan O. T. Hogg, Christine Evers, Patrick A. Naylor
Submitted by:
Aidan Hogg
Last updated:
16 October 2019 - 7:03am
Document Type:
Poster
Document Year:
2019
Event:
Presenters Name:
Aidan Hogg
Paper Code:
1570546902

Abstract 

Abstract: 

Speaker segmentation is an essential part of any diarization system.Applications of diarization include tasks such as speaker indexing, improving automatic speech recognition (ASR) performance and making single speaker-based algorithms available for use in multi-speaker environments.This paper proposes a multiple hypothesis tracking (MHT) method that exploits the harmonic structure associated with the pitch in voiced speech in order to segment the onsets and end-points of speech from multiple, overlapping speakers. The proposed method is evaluated against a segmentation system from the literature that uses a spectral representation and is based on employing bidirectional long short term memory networks (BLSTM). The proposed method is shown to achieve comparable performance for segmenting overlapping speakers only using the pitch harmonic information in the MHT framework.

up
0 users have voted:

Dataset Files

Poster___WASPAA_2019.pdf

(182)