Automatic adaptation of the momel F0 stylisation algorithm to new corpora
نویسندگان
چکیده
The paper investigates the adaptability of the MoMel (Modelling of Melody) Algorithm [1] to new corpora. A detailed overview of the MoMel algorithm and its parameters are presented. The generality of the default parameter values to new corpora is studied empirically. Two of the parameters, related to window durations, are discovered to be highly corpus dependant. The paper presents a significant reduction in the modelling error (r.m.s. from 8.45 to 6.19 Hz) by automatically adapting these two parameters to the new corpora.
منابع مشابه
A Tool for Automatic F0 Stylisation, Annotation and Modelling of Large Corpora
In this paper, an automatic tool for the modelling of F0 contours is presented. The tool is based on Praat, and allows stylisation and annotation of contours, and the definition of global and local patterns, according to the modelling framework described in [1, 2]. The different phases of the process and its application to two corpora of neutral speech are described, and the results of a percep...
متن کاملKorean MULTEXT: A Korean Prosody Corpus
This paper describes the contents of the Korean prosody corpus (Korean MULTEXT), which is a Korean version of the speech database Eurom1. The corpus consists of about 2 hours of read speech, transcribed primarily in orthography (in Korean alphabet and in a Romanized transcription), in IPA and in SAMPA. Furthermore, it includes the original F0 values, stylized F0 values extracted using Momel, an...
متن کاملThe Phonology of Melodic Prominence: the Structure of Melisms
This paper aims at proposing a surface phonological tonal annotation and stylization fitted to the lexical space. More precisely it makes it possible to phonologically structure the F0 variations in prominent words. In previous studies, this specific F0 configuration in such words has been called melism. These principles are integrated in an automatic procedure (INTSMEL) which supplies an autom...
متن کاملComparison of Fujisaki-model extractors and F0 stylizers
This study compares four automatic methods for estimating Fujisaki-model parameters. Since interpolation and smoothing are necessary prerequisites for all approaches their fitting accuracies are also compared with that of a novel stylisation method. A hand-corrected set of results from one of the methods which was created on linguistic grounds served as a second benchmark. Although the four met...
متن کاملEvaluating two versions of the momel pitch modelling algorithm on a corpus of read speech in Korean
The Momel algorithm provides an automatic factoring of raw fundamental frequency into two components: a microprosodic component, corresponding to local variations of pitch caused by the phonetic nature of the speech segments and a macroprosodic component corresponding to the overall pitch pattern of the utterance which is then represented as a sequence of pitch targets. An earlier evaluation es...
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 2004