This paper describes the special demands of conversational speech in the context of corpus-based speech synthesis. The author proposed the CHATR system of prosody-based unit-selection for concatenative waveform synthesis seven years ago, and now extends this work to incorporate the results of an analysis of five-years of recordings of spontaneous conversational speeech in a wide range of actual...

Adaptation to artificially time-compressed speech and natural fast speech has been previously shown in adult listeners, with significant improvement of performance within 5-10 sentences. In the present study, we investigated whether typically developing children also adapt to such variations in speech rate. Eighteen children performed a semantic judgment task on normal speed sentences, natural ...

An extension of HMM-based speech synthesis is proposed to reproduce natural speech sounds. For compression of large amounts of speech, the use of speech synthesizers has an advantage in terms of the size of compressed data. However, the quality of synthetic speech is often inferior to that of speech compressed by general-purpose speech codecs such as CELP, where prosodic features are reproduced...

It has long been assumed that the stress-timed vs. syllabletimed dichotomy is based on perceptual impressions of speech rhythm. However, experimental tests are rare in the literature and not all of them have successfully found perceptual evidence for speech rhythm categorization. Experimental protocols have been very different, sometimes testing naïve vs. non-naïve listeners, sometimes using na...

Speech output is used extensively, including in situations where correct message reception is threatened by adverse listening conditions. Recently, there has been a growing interest in algorithmic modifications that aim to increase the intelligibility of both natural and synthetic speech when presented in noise. The Hurricane Challenge is the first large-scale open evaluation of algorithms desi...

Human utterances demonstrate temporal patterning, also referred to as rhythm. While simple oromotor behaviors (e.g., chewing) feature a salient periodical structure, conversational speech displays a time-varying quasi-rhythmic pattern. Quantification of periodicity in speech is challenging. Unimodal spectral approaches have highlighted rhythmic aspects of speech. However, speech is a complex mu...

The defining property of a Concept-to-Speech system is that it combines language and speech generation. Language generation converts the input concepts into natural language, which speech generation subsequently transforms into speech. Potentially, this leads to a more ‘natural sounding’ output than can be achieved in a plain Text-to-Speech system, since the correct placement of pitch accents a...

An extensive body of research on the perception of synthetic speech carried out over the past 30 years has established that listeners have much more difficulty perceiving synthetic speech than natural speech. Differences in perceptual processing have been found in a variety of behavioral tasks, including assessments of segmental intelligibility, word recall, lexical decision, sentence transcrip...

Jon Barker and Martin Cooke fj.barker,[email protected] Department of Computer Science, University of She eld, She eld, UK ABSTRACT Progress in robust automatic speech recognition may bene t from a fuller account of the mechanisms and representations used by listeners in processing distorted speech. This paper reports on a number of studies which consider how recognisers trained on clean ...