Icassp ' 92 . Dp - Based Determination of F 0 Contours from Speech Signalsa
نویسنده
چکیده
A new algorithm for the determination of fundamental frequency (F0) contours is presented. For each voiced frame appropriate divisors of the frequency with the maximum energy in the spectrum are taken as F0 candidates. An F0 contour is computed using a dynamic programming (DP) method by minimizing a weighted sum of the diierence between consecutive candidates and the distance of the candidates to a predetermined local target value. With this algorithm a coarse error rate of 0.6% on the frame level and of 6.4% on the sentence level is achieved on a German speech database. On the average the diierence to the reference is 1.9 Hz. Our algorithm outperforms two \conventional" algorithms tested on the same data.
منابع مشابه
Prosodic word boundary detection using statistical modeling of moraic fundamental frequency contours and its use for continuous speech recognition
A new method for prosodic word boundary detection in continuous speech was developed based on the statistical modeling of moraic transitions of fundamental frequency (F 0 ) contours, formerly proposed by the authors. In the developed method, F 0 contours of prosodic words were modeled separately according to the accent types. An input utterance was matched against the models and was divided int...
متن کاملNew rule-based and data-driven strategy to incorporate Fujisaki's F 0 model to a text-to-speech system in Castillian Spanish
We will present the analysis of a Spanish prosody database by estimating the parameters of Fujisaki's model for FO contours. These parameters are classified attending to linguistic features and they form the analysis database. When synthesizing FO contours we extract the linguistic features from the text and perform a k-Nearest Neighbour search. Linguistic feature comparison distance is trained...
متن کاملStatistical F0 prediction for electrolaryngeal speech enhancement considering generative process of F0 contours within product of experts framework
We have previously proposed a statistical fundamental frequency (F0) prediction method that makes it possible to predict the underlying F0 contour of electrolaryngeal (EL) speech from its spectral feature sequence. Although this method was shown to contribute to improving the naturalness of EL speech as a whole, the predicted F0 contour was still unnatural compared with that in normal speech. O...
متن کاملCharacterising F(0) contour shape in infant- and foreigner-directed speech
Previous research has used both natural and simulated interactions to investigate the functions of infantdirected speech (IDS), but the effect of these approaches on the results of such studies is unclear. The aim of this study was to compare F(0) contours of natural and simulated speech directed to three distinct speech recipient groups to investigate the effects of different methodologies on ...
متن کاملAccent type recognition and syntactic boundary detection of Japanese using statistical modeling of moraic transitions of fundamental frequency contours
Experiments on accent type recognition and syntactic boundary detection of Japanese speech were conducted based on the statistical modeling of voice fundamental frequency contours formerly proposed by the authors. In the proposed modeling, fundamental frequency contours are segmented into moraic units to generate moraic contours, which are further represented by discrete codes. After modeling t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1992