A Method for Avoiding F0 Discontinuities in a Concatenative Intonation Model
نویسندگان
چکیده
This paper presents a novel approach for avoiding f0 discontinuities in the framework of a unit selection model of intonation with the accent group contour as the basic unit for concatenation. Taking as input the resulting contour of the model, it is modified on an accent group basis according to the typical decomposition into phrase and accent curves of the superpositional models. Results are presented that show a good performance of the proposed method, what implies that it can be a good approach for the treatment of the discontinuities, the main drawback of the concatenative models.
منابع مشابه
A model for the f0 reset in corpus-based intonation approaches
Concatenative intonation systems model the intonation contours as the concatenation of small natural units extracted from suitable contexts. The special characteristics of this type of models make it difficult to include some factors whose effect overcomes the phonic group domain. In this paper one of those factors, the f0 reset related to the sentence internal pauses, is addressed.
متن کاملEmotion conversion using F0 segment selection
This paper describes F0 segment selection, a novel syllablebased F0 conversion method, which provides a concatenative framework to search for F0 segments in a modest corpus of emotional speech (∼15 minutes of data). The method is compared with our earlier work on F0 generation using contextsensitive syllable HMMs. Both methods are complemented with a duration conversion module as well as GMM-ba...
متن کاملUse of pitch pattern improvement in the CHATR speech synthesis system
A corpus-based concatenative speech synthesis system using no signal processing can produce intelligible synthetic speech maintaining original voice characteristics, but it can sometimes be di cult to realize natural prosody. In such a concatenative system, it is very important to select appropriate waveform segments that are naturally close to the target prosody. This paper describes some appr...
متن کاملFeedback loop for prosody prediction in concatenative speech synthesis
We propose a method for concatenative speech synthesis that permits to obtain a better matching between the logF0 and duration predicted by the prosody module and the waveform generation back-end. The proposed method is based upon our previous multilevel parametric F0 model and Toshiba’s plural unit selection and fusion synthesizer. The method adds a feedback loop from the back-end into the pro...
متن کاملComparing spectral distance measures for join cost optimization in concatenative speech synthesis
In concatenative synthesis the join cost function can be related to the probability of a perceived discontinuity at the join. Therefore it is important that the distance measures in the cost function correlate highly with human perceived discontinuities. In this paper the results of a listening test on joins in two Norwegian long vowels: /A:/ and /e:/, is presented. Five spectral distance measu...
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 2006