Simultaneous Speech Detection With Spatial Features for Speaker Diarization
- 23 January 2012
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 20 (2) , 436-446
Abstract
Simultaneous speech poses a challenging problem for conventional speaker diarization systems. In meeting data, a substantial amount of missed speech error is due to speaker overlaps, since usually only one speaker label per segment is assigned. Furthermore, simultaneous speech included in training data can lead to corrupt speaker models and thus worse segmentation performance. In this paper, we propose the use of three spatial cross-correlation-based features together with spectral information for speaker overlap detection on distant microphones. Different microphone-pair data are fused by means of principal component analysis. We have obtained an improvement of the speaker diarization system over the baseline by discarding overlap segments from model training and assigning two speaker labels to them according to likelihoods in Viterbi decoding. In experiments conducted on the AMI Meeting corpus, we achieve a relative DER reduction of 11.2% and 17.0% for single- and multi-site data, respectively. The improvement of clustering with techniques such as beamforming and TDOA-feature stream also leads to a higher effectiveness of the overlap labeling algorithm. Preliminary experiments with NIST RT data show DER improvement on the RT'09 meeting recordings as well.Keywords
This publication has 28 references indexed in Scilit:
- Speaker Diarization for Conference Room: The UPC RT07s Evaluation SystemLecture Notes in Computer Science, 2008
- Speaker indexing and speech enhancement in real meetings / conversations2008
- Progress in the AMIDA Speaker Diarization System for Meeting DataLecture Notes in Computer Science, 2008
- Incremental Learning for Robust Visual TrackingInternational Journal of Computer Vision, 2007
- Unsupervised Learning of Overlapped Speech Model Parameters For Multichannel Speech Activity Detection in Meetings2006
- The AMI Speaker Diarization System for NIST RT06s Meeting DataLecture Notes in Computer Science, 2006
- Source localization in reverberant environments: modeling and statistical analysisIEEE Transactions on Speech and Audio Processing, 2003
- Proximal support vector machine classifiers2001
- Sequential Karhunen-Loeve basis extraction and its application to imagesIEEE Transactions on Image Processing, 2000
- Computer-steered microphone arrays for sound transduction in large roomsThe Journal of the Acoustical Society of America, 1985