Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Feature-Dependent Allophone Clustering

Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama

Japan Advanced Institute of Science and Technology, Tatsu-no-Kuchi, Ishikawa, Japan

We propose a novel method for clustering allophones called Feature-Dependent Allophone Clustering (FD-AC) that determines feature-dependent HMM topology automatically. Existing methods for allophone clustering are based on parameter sharing between the allophone models that resemble each other in behaviors of feature vector sequences. However, all the features of the vector sequences may not necessarily have a common allophone clustering structures It is considered that the vector sequences can be better modeled by allocating the optimal allophone clustering structure to each feature. In this paper, we propose Feature-Dependent Successive State Splitting (FD-SSS) as an implementation of FD-AC. In speaker-dependent continuous phoneme recognition experiments, HMMs created by FD-SSS reduced the error rates by about 10% compared with the conventional HMMs that have a common allophone clustering structure for all the features.


Full Paper

Bibliographic reference.  Matsuda, Shigeki / Nakai, Mitsuru / Shimodaira, Hiroshi / Sagayama, Shigeki (2000): "Feature-dependent allophone clustering", In ICSLP-2000, vol.1, 413-416.