Automatic Extraction of F0 Control Parameters Using Utterance Information
نویسندگان
چکیده
Aiming at automatic extraction of F0 control parameters based on a generation model, we proposed an automatic extraction method using utterance information. In the proposed method, constituent phrase information is used for the prediction of initial value of F0 control parameters in the optimal value search. Extraction experiments using short and long sentence sets showed higher extraction accuracy than the extraction without utterance information. The extraction accuracy difference between single sentence samples and major phrases in long sentences showed the need of further information on neighboring phrases for further improvements of extraction accuracy in long sentences.
منابع مشابه
A 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 کاملAnalysis on command sequences of a F0 generation model for Mandarin speech and its application to their automatic extraction
In this paper, we report on Mandarin F0 characteristics analyses using an F0 generation model and present experimental results on the automatic extraction of their control parameters. To cope with difficulties in automatic extraction of control parameters for F0 generation model proposed by Fujisaki, generation command sequences were extracted and analyzed for two-syllable and three-syllable Ma...
متن کاملCorpus-based Extraction of F0 Co Model Param
A corpus-based method was developed for automatic extraction of the F0 contour generation process model parameters (phrase and accent commands). The method first smoothes the observed F0 contour by a piecewise 3rd order polynomial function and finds points of inflection. Then several parameters related to the points are used as input parameters for the predictor of the model commands. Finally t...
متن کاملImproved Automatic Extraction of Generation Process Model Commands and Its use for Generating Fundamental Frequency Contours for Training HMM-based Speech Synthesis
Generation process model of fundamental frequency (F0) contours can well represent F0 movements of speech keeping a clear relation with linguistic information of utterances. Therefore, by using the model, improvement of HMM-based speech synthesis is expected. One of major problems preventing the use of the model is that the performance of automatic extraction of the model parameters from observ...
متن کاملExtraction of Important Sentenc for Speech Summa
This paper describes speech summarization using F0 information. The speech summarization in this work is realized by the extraction of important sentences from text data transcribed by hand. The important problem in this framework is automatic scoring of sentence importance based on prosodic information from speech wave as well as linguistic information from written text. Prosody conveys nonlin...
متن کامل