DocumentCode :
2264919
Title :
Creation of unseen triphones from diphones and monophones using a speech production approach
Author :
Blomberg, Mats ; Elenius, Kjell
Author_Institution :
Dept. of Speech, Music & Hearing, KTH, Stockholm, Sweden
Volume :
4
fYear :
1996
fDate :
3-6 Oct 1996
Firstpage :
2316
Abstract :
With limited training data, infrequent triphone models for speech recognition are not observed in sufficient numbers. In this paper, a speech production approach is used to predict the characteristics of unseen triphones by concatenating diphones and/or monophones in the parametric representation of a formant speech synthesiser. The parameter trajectories are estimated by interpolation between the endpoints of the original units. The spectral states of the created triphone are generated by the speech synthesiser. Evaluation of the proposed technique has been performed using spectral error measurements and recognition candidate rescoring of N-best lists. In both cases, the created triphones are shown to perform better than the shorter units from which they were constructed
Keywords :
errors; interpolation; parameter estimation; spectral analysis; speech recognition; speech synthesis; N-best lists; concatenation; diphones; formant speech synthesiser; infrequent triphone models; interpolation; limited training data; monophones; parameter trajectory estimation; parametric representation; performance; recognition candidate rescoring; spectral error measurements; spectral states; speech production; unseen triphones; Auditory system; Context modeling; Hidden Markov models; Interpolation; Parameter estimation; Production; Speech recognition; Speech synthesis; Training data; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
Type :
conf
DOI :
10.1109/ICSLP.1996.607271
Filename :
607271
Link To Document :
بازگشت