Rule synthesis of speech from dyadic units

Olive, Joseph P.

doi:10.1109/icassp.1977.1170350

Cited by 33 publications

(18 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, synthesis methods that take into account the context-sensitive nature of phonetic segments and coarticulation phenomena in speech are just as important to intelligibility as detailed formal rules that select and modify the correct target values for the individual phonetic segments themselves. Thus systems that simply concatenate prestored segments such as allophones, diphones, or demisyllables can d. isplay performance ranging from relatively poor quality (such as obtained with the Echo system in the present study) to very high quality [ such as observed with the AT&T Bell Laboratories text-tospeech system (Olive, 1977;Olive and Liberman, 1985 ) ]. In the case of formant synthesis used in high-quality systems such as DECtalk and Prose, a great deal of very detailed acoustic-phonetic knowledge has been formalized in the form of a set of phonetic implementation rules that control the parametric input to the synthesis routines.…”

Section: Discussionmentioning

confidence: 94%

Segmental intelligibility of synthetic speech produced by rule

Logan

Greene

Pisoni

1989

The Journal of the Acoustical Society of America

112

View full text Add to dashboard Cite

This paper reports the results of an investigation that employed the modified rhyme test (MRT) to measure the segmental intelligibility of synthetic speech generated automatically by rule. Synthetic speech produced by ten text-to-speech systems was studied and compared to natural speech. A variation of the standard MRT was also used to study the effects of response set size on perceptual confusions. Results indicated that the segmental intelligibility scores formed a continuum. Several systems displayed very high levels of performance that were close to or equal to scores obtained with natural speech; other systems displayed substantially worse performance compared to natural speech. The overall performance of the best system, DECtalk--Paul, was equivalent to the data obtained with natural speech for consonants in syllable-initial position. The findings from this study are discussed in terms of the use of a set of standardized procedures for measuring intelligibility of synthetic speech under controlled laboratory conditions. Recent work investigating the perception of synthetic speech under more severe conditions in which greater demands are made on the listener's processing resources is also considered. The wide range of intelligibility scores obtained in the present study demonstrates important differences in perception and suggests that not all synthetic speech is perceptually equivalent to the listener.

show abstract

Section: Discussionmentioning

confidence: 94%

Segmental intelligibility of synthetic speech produced by rule

Logan

Greene

Pisoni

1989

The Journal of the Acoustical Society of America

112

View full text Add to dashboard Cite

show abstract

“…Dixon and Maxey (1968) made a special effort to create a unit library for diphone synthesis. Early synthesis research at AT&T based on ''Diadic Units'' (Olive, 1977) demonstrated an alternative to rule-based formant synthesis (Carlson and Granströ m, 1976;Carlson et al, 1982;Klatt, 1982). Charpentier and Stella (1986) opened a new path toward speech synthesis based on waveform concatenation, by introducing the PSOLA model for manipulating pre-recorded waveforms.…”

Section: A Historical Perspective On Concatenative Acoustic Speech Symentioning

confidence: 99%

Data-driven multimodal synthesis

Carlson¹,

Granström²

2005

Speech Communication

View full text Add to dashboard Cite

“…TTS methodology exploits acoustic representations of speech for synthesis, linguistic analysis of text to extract correct pronunciations and prosody in context. The evaluation of speech synthesis systems can be characterized into three folds: (i) accuracy of input text rendering; (ii) intelligibility of the resulting voice message; and (iii) the perceived naturalness of the resulting speech (Olive 1977). Today, TTS applications have been developed for information dissemination in various fields such as medicine, transport services, health, agriculture and weather information dissemination, and education in a wide range of subjects.…”

Section: Introductionmentioning

confidence: 99%

Towards an unrestricted domain TTS system for African tone languages

Ekpenyong

Urua

Gibbon

2008

Int J Speech Technol

View full text Add to dashboard Cite

In this paper we discuss the procedural problems, issues and challenges involved in developing a generic speech synthesizer for African tone languages. We base our development methodology on the "MultiSyn" unitselection approach, supported by Festival Text-To-Speech (TTS) Toolkit for Ibibio, a Lower Cross subgroup of the (New) Benue-Congo language family widely spoken in the southeastern region of Nigeria. We present in a chronological order, the several levels of infrastructural and linguistic problems as well as challenges identified in the Local Language Speech Technology Initiative (LLSTI) during the development process (from the corpus preparation and refinement stage to the integration and synthesis stage). We provide solutions to most of these challenges and point to possible outlook for further refinement. The evaluation of the initial prototype shows that the synthesis system will be useful to non-literate communities and a wide spectrum of applications.

show abstract

Rule synthesis of speech from dyadic units

Cited by 33 publications

References 4 publications

Segmental intelligibility of synthetic speech produced by rule

Segmental intelligibility of synthetic speech produced by rule

Data-driven multimodal synthesis

Towards an unrestricted domain TTS system for African tone languages

Contact Info

Product

Resources

About