PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 7479723

Toward the ultimate synthesis/recognition system.

S Furui
View original source ↗Export metadata ↓

Abstract

This paper predicts speech synthesis, speech recognition, and speaker recognition technology for the year 2001, and it describes the most important research problems to be solved in order to arrive at these ultimate synthesis and recognition systems. The problems for speech synthesis include natural and intelligible voice production, prosody control based on meaning, capability of controlling synthesized voice quality and choosing individual speaking style, multilingual and multidialectal synthesis, choice of application-oriented speaking styles, capability of adding emotion, and synthesis from concepts. The problems for speech recognition include robust recognition against speech variations, adaptation/normalization to variations due to environmental conditions and speakers, automatic knowledge acquisition for acoustic and linguistic modeling, spontaneous speech recognition, naturalness and ease of human-machine interaction, and recognition of emotion. The problems for speaker recognition are similar to those for speech recognition. The research topics related to all these techniques include the use of articulatory and perceptual constraints and evaluation methods for measuring the quality of technology and systems.

Explore related subjects

CommunicationCommunication Devices for People with DisabilitiesComputersHumansLanguageLinguisticsPerceptionPhonationSpeechTelecommunicationsUser-Computer InterfaceVoiceJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

S Furui. 1995-10-24. Toward the ultimate synthesis/recognition system.. https://doi.org/10.1073/pnas.92.22.10040

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

Information-sharing among couples considering multifetal pregnancy reduction.

OBJECTIVE: To determine the information-sharing strategies of couples considering fetal reduction, and the impact of these strategies on the chances of encountering hostility in their social networks. DESIGN: Cross-sectional design of semistructured qualitative interviews, coded with respect to sharing strategies and level of personally directed hostility encountered. SETTING: Multiple Pregnancy Management Program, Comprehensive Genetics, New York, New York. PATIENT(S) AND INTERVENTION(S): Fifty women and their partners who were making a first visit to our maternal-fetal management facility, in order to consider the possibility of multifetal reduction as a pregnancy-management strategy. MAIN OUTCOME MEASURE(S): Development of information-sharing strategies, and the chances of encountering personally directed hostility regarding multifetal reduction associated with more and less selective strategies. RESULT(S): Four information-sharing strategies emerged from the analysis. Two of these strategies were relatively open (extended network, and both parents). Two other strategies were relatively selective (qualified family and friends, and defended relationship). The selective strategies were significantly less likely to encounter to encounter personally directed hostility (odds ratio, 3.88; 95% confidence intervals, 0.87-17.30). CONCLUSION(S): Selective sharing of information for couples considering multifetal prgnancy reduction is a potentially useful strategy for moderating potentially stressful relationships in their social networks. Clinics should find a way of integrating the discussion of selective sharing into their clinic's cultural repertoire of patient-support services.

Communication↗