대한음성학회:학술대회논문집 (Proceedings of the KSPS conference)
- 대한음성학회 2005년도 춘계 학술대회 발표논문집
- /
- Pages.87-90
- /
- 2005
Subspace distribution clustering hidden Markov model을 위한 codebook design
Codebook design for subspace distribution clustering hidden Markov model
- Cho, Young-Kyu (Speech Information Processing Lab., Department of Computer Science and Engineering, Korea Univ.) ;
- Yook, Dong-Suk (Speech Information Processing Lab., Department of Computer Science and Engineering, Korea Univ.)
- 발행 : 2005.04.27
초록
Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.
키워드