Optimized Selection of Intonation Dictionaries in Corpus Based Intonation Modelling
نویسنده
چکیده
Data scarcity in corpus-based intonation modelling for TTS applications is addressed. We propose to apply a searching process to a list of dictionaries of classes of intonation patterns previously trained from corpus to avoid problems associated with the scarce number of samples in the classes. Results indicate that better results are obtained in comparison with previous alternatives where the probability of predicting a less representative intonation pattern has been shown to be higher.
منابع مشابه
Optimized selection of intonation dictionaries in corpus based intonation modelling
Data scarcity in corpus-based intonation modelling for TTS applications is addressed. We propose to apply a searching process to a list of dictionaries of classes of intonation patterns previously trained from corpus to avoid problems associated with the scarce number of samples in the classes. Results indicate that better results are obtained in comparison with previous alternatives where the ...
متن کاملModelling Japanese intonation using PENTAtrainer2
This paper presents results from Japanese intonation modelling using PENTAtrainer2, an articulatory synthesiser. Our first aim is to show that PENTA, on which PENTAtrainer2 is based, can achieve high accuracy in predictive synthesis of varying intonation contours. We trained the synthesiser on a 6251-sentence functionally annotated corpus and generated F0 contours for each communicative conditi...
متن کاملApplying data mining techniques to corpus based prosodic modeling
This article presents MEMOInt, a methodology to automatically extract the intonation patterns which characterize a given corpus, with applications in text-to-speech systems. Easy to understand information about the form of the characteristic patterns found in the corpus can be obtained from MEMOint in a way which allows easy comparison with other proposals. A visual representation of the relati...
متن کاملA proposal to quantitatively select the right intonation unit in data-driven intonation modeling
In this work, we provide a procedure for the systematic evaluation of the quantitative impact of the selection of the basic intonation unit for data-driven intonation modeling. Taking advantage of the corpus based modeling technique previously developed, we show how the number of prosodic features selected and the kind of basic unit determines the final prediction RMSE of the synthesized F0 pro...
متن کاملAnalysis and Modelling of Question Intonation in American English
This paper addresses the modelling in text-to-speech of the rising intonation pattern in American English which is often found in yes-no questions. A small corpus containing yes-no questions was recorded and analysed. F0 was then modelled using an automatic procedure. The paper also reports on the stability of alignment of F0 targets in rising intonation patterns.
متن کامل