Speech parameter generation from HMM using dynamic features
作者： K. Tokuda , T. Kobayashi , S. Imai
DOI: 10.1109/ICASSP.1995.479684
关键词:
摘要: This paper proposes an algorithm for speech parameter generation from HMMs which include the dynamic features. The performance of recognition based on has been improved by introducing features speech. Thus we surmise that, if there is a method features, it will be useful synthesis rule. It shown that using results in searching optimum state sequence and solving set linear equations each possible sequence. We derive fast solution analogy RLS adaptive filtering. also show effect incorporating example generation.
ieeecomputersociety.org参考文章(5)
S Haykin, Adaptive Filter Theory ,(1986)
S. Furui, Speaker-independent isolated word recognition using dynamic features of speech spectrum IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 34, pp. 52- 59 ,(1986) , 10.1109/TASSP.1986.1164788
T. Fukada, K. Tokuda, T. Kobayashi, S. Imai, An adaptive algorithm for mel-cepstral analysis of speech international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 137- 140 ,(1992) , 10.1109/ICASSP.1992.225953
S. Imai, Cepstral analysis synthesis on the mel frequency scale international conference on acoustics, speech, and signal processing. ,vol. 8, pp. 93- 96 ,(1983) , 10.1109/ICASSP.1983.1172250
A. Ljolje, F. Fallside, Synthesis of natural sounding pitch contours in isolated utterances using hidden Markov models IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 34, pp. 1074- 1080 ,(1986) , 10.1109/TASSP.1986.1164948