作者: Kazuhiko Iwata
DOI: 10.1121/1.417892
关键词: Computer science 、 Part of speech 、 Intonation (linguistics) 、 Sentence 、 Adjective 、 Word (group theory) 、 Syntactic structure 、 Adverb 、 Noun 、 Verb 、 Speech recognition 、 Linguistics
摘要: A pitch pattern defining intonation for a text-to-speech system is generated in accordance with part of speech (e.g., noun, verb, adjective, adverb, etc.) each word which can be determined more accurately than the syntactic structure sentence. The response to combinations parts adjacent words sentence based on fact that any combination two at both sides boundary reflects strength connection meaning words.