Prosodic models have been extensively applied in speech synthesis. However, the necessity of synthesizing prosody has as yet not resulted in a generally agreed upon approach to prosodic modeling. This statement holds for the assignment of segmental durations as well as for generating F0 curves, the acoustic correlate of intonation contours. This paper concentrates on the use and usability of in...

Human readings of structured documents exhibit a much richer intonation than that observed in read isolated sentences. It is a challenge to capture this richness in an automatic way using datadriven techniques. In this paper, we extend our previous research on intonation modelling for isolated sentences in different respects: (i) the RNN (Recurrent Neural Network) intonation model is now traine...

Manifestation of the question intonation was investigated for Ryukyuan which is an endangered language. Ryukyuan is related to Japanese and is known to preserve a number of linguistic features that were present in 6 to 8 th century Japanese. Ryukyuan is typologically interesting since the mood suffix takes the role of intonation. Though a language with such a mood suffix has been reported in li...

For approximately one century, the study of Intonation has attracted a great deal of scholarly attention, despite the notorious difficulty to analyse by ear this evasive property of spoken language. Probably, the chief impetus to this long-standing effort stems from the conviction that speech melody has a particular communicative value. Indeed, individual speech sounds do not carry an intrinsic...

This study compared sentence intonation of L1 Mandarin by native speakers and L2 Mandarin by Cantonese learners, with both acoustic analysis and perceptual experiment. Three types of sentences (i.e., statement, intonation question, and particle question) ending with different tones and in different lengths were investigated. The perceptual experiment showed that declarative intonation in L2 spe...

This article discusses speech production in dialogue from the perspective of natural language generation focusing on the selec tion of appropriate intonation We argue that in order to assign ap propriate intonation contours in speech producing systems it is vital to acknowledge the diversity of functions that intonation ful lls and to account for communicative and immediate contexts as major fa...

Much is already known about the prosodic systems of the indigenous South African languages from descriptions and analyses in the existing literature. All of the existing work has been carried out in the field of African studies or formal linguistics. In order to be able to implement the generalisations obtained into computational models in speech processing, the existing sources and results mus...