Intonation recognition for indonesian speech based on fujisaki model
نویسندگان
چکیده
In this paper, we proposed to use the Fujisaki parameter to distinguish between declarative and interrogative intonation in Indonesian speech. Four combinations of Fujisaki parameter were selected as the features to distinguish between declarative and interrogative intonation. The first combination is only the amplitude of last accent command. The second combination consists of the amplitude of last accent command and the magnitude of last phrase command. The third combination consists of Fb, the amplitude of last accent command, and the magnitude of last phrase command. The fourth combination consists of Fb/100, the amplitude of last accent command, and the magnitude of last phrase command. The recognition rates using the neural network were 83.33 %, 90.00 %, 50.00 %, and 96.67 % for each combination. The highest recognition rate was achieved by using Fb/100, the last accent command amplitude and the last phrase command amplitude as its inputs.
منابع مشابه
N-Best Rescoring based on Intonation Prediction for a Spanish ASR System
This paper presents a novel method for rescoring the n-best recognition hypotheses using intonation knowledge. The model synthesizes the f0 contours for each of the n-best hypotheses and estimates an intonative matching index between the synthetic shapes and the real f0 contour. This index is applied in the rescoring process, and can be viewed as a degree of intonation compatibility between the...
متن کاملA quantitative description of German prosody offering symbolic labels as a by-product
The prosodic quality of a text-to-speech system is important for the intellegibility and perceived naturalness of synthetic speech. In earlier works the author developed a linguistically motivated model of German intonation based on the quantitative Fujisaki model of the production process of F0. The current paper compares results yielded by automatic Fujisaki modeling with a GToBI-style anotat...
متن کاملA novel approach to the fully automatic extraction of Fujisaki model parameters
The generation of naturally-sounding F0 contours in TTS is important for the intellegibility and perceived naturalness of synthetic speech. In earlier works the author developed a linguistically motivated model of German intonation based on the quantitative Fujisaki model of the production process of F0. The extraction of parameters for this model from the extracted F0 contour, however, poses p...
متن کاملThe influence of speech rate on Fujisaki model parameters
The current paper examines influences of speech rate on Fujisaki model parameters based on read speech from the BonnTempo-Corpus containing productions by 12 native speakers of German at five different intended tempo levels (very slow, slow, normal, fast, fastest possible). The normal condition was produced at an average rate of 6.34 syllables/s or 100%, the very slow version at 67%, and the fa...
متن کاملEstimation of the parameters of the quantitative intonation model with continuous wavelet analysis
Intonation generation in state-of-the-art speech synthesis requires the analysis of a large amount of data. Therefore reliable algorithms for the extraction of the parameters of an intonation model from a given F0 contour are required. This contribution proposes improvements concerning the extraction of the parameters of the quantitative intonation model developed by Fujisaki. The improvements ...
متن کامل