Speaker segmentation and adaptation for speech recognition on multiple-speaker audio conference data
IEEE International Conference onMultimedia and Expo, ICME 2007, Beijing, Çin, 2 - 05 Temmuz 2007, ss.192-195, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/icme.2007.4284619
- Basıldığı Şehir: Beijing
- Basıldığı Ülke: Çin
- Sayfa Sayıları: ss.192-195
- Boğaziçi Üniversitesi Adresli: Evet
Özet
In this paper, we address the problem of how to improve the automatic speech recognition (ASR) performance on audio conference data by speaker segmentation and speaker adaptation. A new speaker segmentation method is proposed, where the speaker turns and speaker labels are automatically determined. For speaker adaptation, we use Vocal Tract Length Normalization and Maximum Likelihood Linear Regression. On a corpus of multi-speaker teleconferences, the word error rate of the ASR system improves over 4% absolute. © 2007 IEEE.