Prosodic and other Long-Term Features for Speaker Diarization
Authors:
- 5 June 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 17 (5) , 985-993
Abstract
Speaker diarization is defined as the task of determining ldquowho spoke whenrdquo given an audio track and no other prior knowledge of any kind. The following article shows how a state-of-the-art speaker diarization system can be improved by combining traditional short-term features (MFCCs) with prosodic and other long-term features. First, we present a framework to study the speaker discriminability of 70 different long-term features. Then, we show how the top-ranked long-term features can be combined with short-term features to increase the accuracy of speaker diarization. The results were measured on standardized datasets (NIST RT) and show a consistent improvement of about 30% relative in diarization error rate compared to the best system presented at the NIST evaluation in 2007.Keywords
This publication has 20 references indexed in Scilit:
- Higher-Level Features in Speaker Recognition2007
- A fast-match approach for robust, faster than real-time speaker diarization2007
- How Is Individuality Expressed in Voice? An Introduction to Speech Production and Description for Speaker Classification2007
- Hybrid Speaker-Based Segmentation System Using Model-Level Clustering2006
- Modeling prosodic feature sequences for speaker recognitionSpeech Communication, 2005
- The ICSI Meeting Corpus2003
- Harmonics-to-Noise RatioJournal of Voice, 2002
- DISTBIC: A speaker-based segmentation for audio data indexingSpeech Communication, 2000
- Speaker recognition: a tutorialProceedings of the IEEE, 1997
- A Probabilistic Distance Measure for Hidden Markov ModelsAT&T Technical Journal, 1985