In this paper we investigate whether it is possible to combine speech data from two South African accents of English in order to improve speech recognition in any one accent. Our investigation is based on Afrikaans-accented English and South African English speech data. We compare three acoustic modelling approaches: separate accent-specific models, accentindependent models obtained by straight...

Realizing expressive text-to-speech synthesis needs both text processing and the rendering of natural expressive speech. This paper focuses on the former as a front-end task in the production of synthetic speech, and investigates a novel method for predicting emphasized accent phrases from advertisement text information. For this purpose, we examine features that can be accurately extracted by ...

We have formerly proposed a statistical model of moraic transitions of fundamental frequency (F0) contours and showed its e ectiveness for prosodic boundary detection and accent type recognition. This model represented F0 contours of prosodic words to simultaneously detect and recognize prosodic word boundaries and accent types. This paper proposes a method where prosodic word F0 contours are m...

The ability to automatically identify a speaker’s accent would be very useful for a speech recognition system as it would enable the system to use both a pronunciation dictionary and speech models specific to the accent, techniques which have been shown to improve accuracy. Here, we describe some experiments in unsupervised accent classification. Two techniques have been investigated to classif...

This work investigates the tonal structure of the focal accent in narrow focus statements of Neapolitan Italian. The formal properties of this accent lend themselves to two competing analyses. Specifically, this accent could equally be described as a HL accentual fall or as a LH rise. The two analyses were evaluated on the basis of a set of utterances containing focus constituents with varying ...

A method was developed to utilize linguistic information (lexical accent types and syntactic boundaries) to improve the performance of the automatic extraction of the F0 contour generation process model commands. The extraction scheme is first to smooth the observed F0 contour by a piecewise 3rd order polynomial function and to locate accent command positions by taking the derivative of the fun...

This work investigates the tonal structure of the focal accent in narrow focus statements of Neapolitan Italian. The formal properties of this accent lend themselves to two competing analyses. Specifically, this accent could equally be described as a HL accentual fall or as a LH rise. The two analyses were evaluated on the basis of a set of utterances containing focus constituents with varying ...

In Hungarian, focussed elements occur in certain syntactic positions. Because of this limitation, prominence marking by means of prosody is less salient than in languages where focus can be expressed by accent shift without changes in word order. In this study, we examined Hungarian utterances that were identical in their segmental structure, but differed with regard to their semantic and pragm...

This study examines the phonetic correlates of stress and accent in Catalan, analyzing syllable duration, spectral balance, vowel quality, and overall intensity in two stress [stressed, unstressed] and in two accent conditions [accented, unaccented]. Catalan reveals systematic phonetic differences between accent and stress, consistent with previous work on Dutch, English, and Spanish (Slujter &...