This paper presents our research in preparation to compile a Lithuanian intonation corpus. The main objective of this research was to discover characteristic patterns of Lithuanian intonation through clustering of pitch contours of intermediate intonation phrases. The paper covers the set of procedures that were used to extend an ordinary speech corpus to make it suitable for intonation analysi...

This study investigated intonation of Japanese sentences spoken by Australian English speakers and the influence of their first language (L1) prosody. The second language (L2) intonation is a complicated product of the L1 transfer at two levels of prosodic hierarchy, at word level and at phrase levels. For each level, the typical error patterns were listed and described in terms of L2 acquisiti...

Intonation, long thought to be a key to effectiveness in spoken language, is more and more commonly addressed in English language teaching through the use of speech visualization technology. While the use of visualization technology is a crucial advance in the teaching of intonation, such teaching can be further enhanced by connecting technology to an understanding of how intonation functions i...

This paper presents a study on the role of pitch targets in the manifestation of Chinese tone and intonation. Pitch targets are particularly measured as (fundamental frequency) peaks and valleys over time. Analysis and perceptual experiments were conducted on 72 sentences, each with almost identical tone mapping, uttered two times by a female native in statements or questions. The tone and into...

This paper is a progress report on a project in linguistically based automatic speech recognition, The domain of this project is English intonation. The system I will describe analyzes fundamental frequency contours (F0 contours) of speech in terms of the theory of melody laid out in Pierrehumbert (1980). Experiments discussed in Liberman and Pierrehumbert (1983) support the assumptions made ab...

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 ...

Most speakers in today’s societies are bilingual or multilingual and linguistic research has shown that the grammatical systems of two or more languages interact in speech production and perception [11,13]. The confrontation of two or more competing phonological systems and their phonetic realization leads to what we generally understand as a “foreign accent”. The interference appears on the se...

Intonation, when used in a narrow sense, refers to fundamental frequency (henceforth F0) patterns in speech that convey information beyond lexical meanings. In a broader sense, intonation also includes other suprasegmental patterns such as duration, intensity and voice quality, etc., that also convey non-lexical meanings. This article will focus mainly on the former, because, as will be seen, F...

This paper proposes an HMM-based approach to generating emotional intonation patterns. A set of models were built to represent syllable-length intonation units. In a classification framework, the models were able to detect a sequence of intonation units from raw fundamental frequency values. Using the models in a generative framework, we were able to synthesize smooth and natural sounding pitch...

This study’s aim is to predict speaker personality from intonation patterns in spoken dialogs. Intonation patterns were extracted by a parametric superpositional stylization approach that allows for pattern description on a parametric as well as on a categorical level. Based on features derived from these representations we trained support vector machines and fitted generalized linear regressio...