Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Multi-Stream Speaker Diarization Systems for the Meetings Domain

Ascensión Gallardo-Antolín (1), Xavier Anguera (2), Chuck Wooters (2)

(1) Universidad Carlos III de Madrid, Spain; (2) International Computer Science Institute, USA

In the context of speech and speaker recognition systems, it is well known that the combination of different feature streams can improve significantly their performance. However, the application of multi-stream (MS) techniques to speaker diarization systems has not been extensively studied. In this paper, we address this issue: we formulate different MS techniques, such as feature combination, probability combination and selection, for their specific application to the segmentation and clustering modules of a speaker diarization system. We evaluate the different methods proposed for the meetings domain (RT04s database) and two different pairs of streams: first, MFCC and PLP and second, MFCC and prosodic features. For both types of multi-streams, results show that the MS probability combination approach applied to the segmentation stage clearly outperforms the single-stream, MS feature combination and MS selection systems.

Full Paper

Bibliographic reference.  Gallardo-Antolín, Ascensión / Anguera, Xavier / Wooters, Chuck (2006): "Multi-stream speaker diarization systems for the meetings domain", In INTERSPEECH-2006, paper 1620-Thu1A1O.3.