This paper presents a Brazilian Portuguese TTS based on HMMs, which uses mel-cepstral coefficients as parameters of speech. We implemented an algorithm which performs a phoneme-based transcription to the Portuguese spoken in Rio de Janeiro. For a given text to be synthesized, after the phoneme transcription, static features are extracted from a sentence HMM, generated by concatenating HMMs sub-word units. An algorithm for choosing the best set of those speech units was also developed. Subjective tests show that the proposed TTS gives better results than a PSOLA based on syllabic units, with the advantage of easy speaker adaptation.
Resumo-Este trabalho apresenta uma análise comparativa que tem como objetivo investigar a influência da classe gramatical das palavras em sistemas de síntese de fala para o português brasileiro baseados em modelos escondidos de Markov. Três versões do sintetizador foram comparadas: (1) com informac ¸ão completa de classe gramatical; (2) somente com a diferenciac ¸ão entre palavra de conte údo e palavra de contexto e (3) sem qualquer informac ¸ão de classe gramatical. Os resultados indicam que a presenc ¸a da informac ¸ão de classe gramatical traz pouca influência na qualidade da voz sintetizada. A vers ão com distinc ¸ão entre palavra de conte údo e de contexto leva a resultados similares aos obtidos quando utilizada a informac ¸ão gramatical completa, com um menor custo computacional.
This paper focuses on the second edition of the Vocabulário Ortográfico da Língua Portuguesa, the reference book for Brazilian Portuguese orthography. The new edition, published in 1998, has absorbed a great number of foreign words with their original spelling. There follows from that novelty a confusing guide to Portuguese orthography.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.