Technical Improvements of the E-HMM Based Speaker Diarization System for Meeting Records
This paper is concerned with the speaker diarization task in the specific context of the meeting room recordings. Firstly, different technical improvements of an E-HMM based system are proposed and evaluated in the framework of the NIST RT’06S evaluation campaign. Related experiments show an absolute gain of 6.4% overall speaker diarization error rate (DER) and 12.9% on the development and evaluation corpora respectively.
Secondly, this paper presents an original strategy to deal with the overlapping speech. Indeed, speech overlaps between speakers are largely involved in meetings due to the spontaneous nature of this kind of data and they are responsible for a decrease in performance of the speaker diarization system, if they are not dealt with. Experiments still conducted in the framework of the NIST RT’06S evaluation show the ability of the strategy in detecting overlapping speech (decrease of the missed speaker error rate), even if an overall gain in speaker diarization performance has not been achieved yet.
KeywordsSelection Technique Technical Improvement Speaker Recognition Baseline System Speech Segment
Unable to display preview. Download preview PDF.
- 1.AMI: Augmented Multi-party Interaction project, http://www.amiproject.org/
- 2.CHIL: Computers in the Human Interaction Loop project, http://chil.server.de/servlet/is/101/
- 3.NIST: Spring 2006 (RT 2006S) Rich Transcription meeting recognition ev- aluation plan (2006), http://www.nist.gov/speech/tests/rt/rt2006/spring/docs/rt06s-meeting-eval-plan-V2.pdf
- 5.Meignier, S., Moraru, D., Fredouille, C., Bonastre, J.F., Besacier, L.: Step-by-step and integrated approaches in broadcast news speaker diarization. Special issue of Computer and Speech Language Journal 20(2-3) (2006)Google Scholar
- 6.Moraru, D., Meignier, S., Fredouille, C., Besacier, L., Bonastre, J.F.: The ELISA consortium approaches in broadcast news speaker segmentation during the NIST 2003 rich transcription evaluation. In: ICASSP 2004, Montreal, Canada (2004)Google Scholar
- 7.Zhu, X., Barras, C., Meignier, S., Gauvain, J.L.: Combining speaker identification and BIC for speaker diarization. In: EuroSpeech 2005, Lisboa, Portugal (2005)Google Scholar
- 8.Bonastre, J.F., Wils, F., Meignier, S.: ALIZE, a free toolkit for speaker recognition. In: ICASSP 2005, Philadelphia, USA (2005)Google Scholar
- 9.Meignier, S., Bonastre, J.F., Fredouille, C., Merlin, T.: Evolutive HMM for speaker tracking system. In: ICASSP 2000, Istanbul, Turkey (2000)Google Scholar
- 10.Anguerra, X., Wooters, C., Peskin, B., Aguilo, M.: Robust speaker segmentation for meetings: the icsi-sri spring 2005 diarization system. In: Rich Transcription 2005 Spring Meeting Recognition Evaluation, Edinburgh, Scotland (2005)Google Scholar
- 11.Ajmera, J., Wooters, C.: A robust speaker clustering algorithm. In: ASRU 2003, US Virgin Islands, USA (2003)Google Scholar
- 12.Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted gaussian mixture models. Digital Signal Processing (DSP), a review journal - Special issue on NIST 1999 speaker recognition workshop 10, 19–41 (2000)Google Scholar
- 13.Pelecanos, J., Sridharan, S.: Feature warping for robust speaker verification. In: 2001: A Speaker Odyssey. The Speaker Recognition Workshop, Chania, Crete, pp. 213–218 (2001)Google Scholar
- 14.Reynolds, D.A.: Channel robust speaker verification via feature mapping. In: ICASSP 2003 Conference, Hong Kong, China (2003)Google Scholar
- 15.Bonastre, J.F., Fredouille, C., Scheffer, N.: LIA 2005 system description. In: NIST SRE 2005 Workshop: speaker recognition evaluation campaign, Montreal, Canada (2005)Google Scholar