Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Extraction of Reliable Transformation Parameters for Unsupervised Speaker Adaptation

Jen-Tzung Chien (1), Jean-Claude Junqua (2), Philippe Gelin (2)

(1) Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan
(2) Speech Technology Laboratory, Panasonic Technologies Inc., Santa Barbara, CA, USA

Adaptation of speaker-independent hidden Markov models (HMMís) to a new speaker using speaker-specific data is an effective approach to reinforce speech recognition performance for the enrolled speaker. Practically, it is desirable to flexibly perform the adaptation without any knowledge or limitation on the enrolled adaptation data (e.g. data transcription, length and content). However, the inevitable transcription errors on adaptation data may cause unreliability in model adaptation. The variable amount and content of adaptation data require the algorithm to dynamically control the degrees of sharing in transformation-based adaptation. This paper presents an unsupervised hierarchical adaptation algorithm where a tree structure of HMMís is incorporated to control the transformation sharing. To extract reliable transformation parameters, we exploit the reliability assessment criteria using the confidence measure and description length. Experiments show that the unsupervised speaker adaptation with reliability assessment can significantly improve the recognition performance for any lengths of adaptation data.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Chien, Jen-Tzung / Junqua, Jean-Claude / Gelin, Philippe (1999): "Extraction of reliable transformation parameters for unsupervised speaker adaptation", In EUROSPEECH'99, 207-210.