Estimating tonal prosodic discontinuities in Spanish using HMM. Bassi, A.; Becerra, N.; and Loncomilla, P. Speech Communication, 48(9):1112-1125, September.
Paper doi abstract bibtex The tonal prosodic discontinuity estimation in Spanish is exhaustively modelled using HMM. Due to the high morphological complexity in Spanish, a relatively coarse grammatical categorization is tested in two sorts of texts (sentences from newspapers and a theatre play). The estimation of the type of discontinuity (falling or rising tones) at the boundary of intonation groups is assessed. The HMM approach is tested with: (a) modelling the observation probability with monograms, bigrams and full-window probability; (b) state duration modelling; (c) discriminative analysis of intermediate and final observation vectors and (d) penalization scheme in Viterbi decoding. The optimal configurations led to reductions of 3% or 5% in error detection. The estimation of the observation probability with monograms and bigrams leads to worse results than the ordinary full-window probability, although they provide better generalization. Nevertheless, the performance of the monograms and bigrams approximation can be enhanced if applied in combination with state duration constraints.
@article{bassi_estimating_2006,
Author = {Bassi, Alejandro and Becerra, Néstor and Loncomilla, Patricio},
Date = {2006},
Date-Modified = {2017-04-19 08:04:06 +0000},
Doi = {10.1016/j.specom.2006.03.006},
Issn = {01676393},
Journal = {Speech Communication},
Keywords = {phonetics, prosody, Spanish, speech recognition, speech technology},
Month = sep,
Number = {9},
Pages = {1112-1125},
Title = {Estimating tonal prosodic discontinuities in Spanish using HMM},
Url = {http://dx.doi.org/10.1016/j.specom.2006.03.006 http://linkinghub.elsevier.com/retrieve/pii/S0167639306000288},
Volume = {48},
Abstract = {The tonal prosodic discontinuity estimation in Spanish is exhaustively modelled using HMM. Due to the high morphological complexity in Spanish, a relatively coarse grammatical categorization is tested in two sorts of texts (sentences from newspapers and a theatre play). The estimation of the type of discontinuity (falling or rising tones) at the boundary of intonation groups is assessed. The HMM approach is tested with: (a) modelling the observation probability with monograms, bigrams and full-window probability; (b) state duration modelling; (c) discriminative analysis of intermediate and final observation vectors and (d) penalization scheme in Viterbi decoding. The optimal configurations led to reductions of 3\% or 5\% in error detection. The estimation of the observation probability with monograms and bigrams leads to worse results than the ordinary full-window probability, although they provide better generalization. Nevertheless, the performance of the monograms and bigrams approximation can be enhanced if applied in combination with state duration constraints.},
Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.specom.2006.03.006%20http://linkinghub.elsevier.com/retrieve/pii/S0167639306000288},
Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.specom.2006.03.006}}