Speech synthesis from text

Sagisaka, Yoshinori

doi:10.1109/35.46669

Cited by 13 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The average MOS rating for each stimulus (TTS utterance) was later calculated and tabulated. As these tests were aimed at assessing the segmental as well as the suprasegmental characteristics, [14] the volunteers took further listening tests of a prepared list of 20 sentences and were asked to rate these using MOS. A sample is given in Table 3.…”

Section: Resultsmentioning

confidence: 99%

Developing a Child Friendly Text-to-Speech System

Jacob

Mythili

2008

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

This paper discusses the implementation details of a child friendly, good quality, English text-to-speech (TTS) system that is phoneme-based, concatenative, easy to set up and use with little memory. Direct waveform concatenation and linear prediction coding (LPC) are used. Most existing TTS systems are unit-selection based, which use standard speech databases available in neutral adult voices. Here reduced memory is achieved by the concatenation of phonemes and by replacing phonetic wave files with their LPC coefficients. Linguistic analysis was used to reduce the algorithmic complexity instead of signal processing techniques. Sufficient degree of customization and generalization catering to the needs of the child user had been included through the provision for vocabulary and voice selection to suit the requisites of the child. Prosody had also been incorporated. This inexpensive TTS system was implemented in MATLAB, with the synthesis presented by means of a graphical user interface (GUI), thus making it child friendly. This can be used not only as an interesting language learning aid for the normal child but it also serves as a speech aid to the vocally disabled child. The quality of the synthesized speech was evaluated using the mean opinion score (MOS).

show abstract

Section: Resultsmentioning

confidence: 99%

Developing a Child Friendly Text-to-Speech System

Jacob

Mythili

2008

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

show abstract

“…A síntese de fala é a produção de voz por máquinas, a partir da fonetização automática de frases (DUTOIT, 1997). Ao contrário da simples reprodução de voz, essa síntese objetiva um resultado equivalente à produção da fala humana, com informações fonéticas e prosódicas correspondentes (SAGISAKA, 1990).…”

Section: Introductionunclassified

Prosódia e síntese da fala: uma revisão integrativa da literatura

Galdino

Oliveira

2023

RAbralin

View full text Add to dashboard Cite

Este é um trabalho de revisão integrativa acerca de estudos feitos entre as relações da prosódia e da síntese de fala. A partir da pergunta de pesquisa “Como a prosódia tem sido considerada em trabalhos que visam o aprimoramento da síntese de fala?”, realizamos uma busca no Google Scholar com a sintaxe (prosódia OR entoação OR “frequência fundamental”) AND ("text-to-speech" OR TTS OR "síntese de fala" OR “síntese da fala”). Avaliamos os títulos e os resumos dos estudos e, mediante a observação de critérios de inclusão e de exclusão, encontramos 10 estudos, entre 2010 e 2021, que dissertam sobre prosódia e síntese de fala. Os trabalhos selecionados indicam que a frequência fundamental (ou pitch) é o recurso mais expressivo para o aprimoramento da fala sintética, embora os sistemas de conversão de texto para a fala utilizem outras características prosódicas para aprimorar seu desempenho. Além disso, os resultados desta revisão mostraram que há ainda pouco estudo no Brasil sobre a relação entre a prosódia e a síntese de fala e que é importante a pesquisa conjunta entre pesquisadores de áreas da linguística e das engenharias, a fim de se obter melhores resultados em sistemas de síntese de fala.

show abstract

“…Speech input proved to be neither faster nor slower than navigation with the mouse. Playback of digitally recorded speech for fixed text has long been possible; however, high quality textto-speech synthesis for arbitrary text is also now possible [25]. Considerable research has been done to identify non-speech sounds for use in sound enhanced interfaces [11,12,7,8].…”

Section: Introductionmentioning

confidence: 99%

Adapting graphical user interfaces for use by visually handicapped computer users: Current results and continuing research

Karshmer

Ogden

Brawner

et al. 1994

Computers for Handicapped Persons

View full text Add to dashboard Cite

ABSTRACT. The use of modern computers and software by the visually handicapped has become more difficult over the past few years. In earlier systems the user interface was a simple character based environment. In those systems, simple devices like screen readers~ braille output and speech synthesizers were effective. Current systems now run Graphical User Interfaces (GUIs) which have rendered these simple aids almost useless. In no area has this problem become more important than in technologies for the handicapped. What has become enabling technology for the sighted has become disabling technology for the visually impaired. In the current work we discuss new and innovative approaches to permit non-sighted users to interface with GUIs, having the salutary effect of gaining needed access to the most modern computing equipment for a subset of our population that is otherwise excluded from such access. Using our approach to integrating special interfaces into those already shipped by the manufacturer, the non-sighted user will no longer be isolated from the mainstream of the information world. The net effect of such an interface is to make computing and information resources available to the visually handicapped user at the cost as to the sighted user.

show abstract

Speech synthesis from text

Cited by 13 publications

References 19 publications

Developing a Child Friendly Text-to-Speech System

Developing a Child Friendly Text-to-Speech System

Prosódia e síntese da fala: uma revisão integrativa da literatura

Adapting graphical user interfaces for use by visually handicapped computer users: Current results and continuing research

Contact Info

Product

Resources

About