Results 51 to 60 of about 371,452 (184)
Pauses and the temporal structure of speech [PDF]
, 1994 Natural-sounding speech synthesis requires close control over the temporal structure of the speech flow. This includes a full predictive scheme for the durational structure and in particuliar the prolongation of final syllables of lexemes as well as for ...
Zellner, Brigitte
core +1 more source
Deep Learning for Mandarin-Tibetan Cross-Lingual Speech Synthesis
IEEE Access, 2019 This paper proposes a deep learning-based Mandarin-Tibetan cross-lingual speech synthesis to realize both Mandarin speech synthesis and Tibetan speech synthesis under a unique framework.
Weizhao Zhang +3 more
doaj +1 more source
Research on a Mongolian Text to Speech Model Based on Ghost and ILPCnet
Applied SciencesThe core challenge of speech synthesis technology is how to convert text information into an audible audio form to meet the needs of users. In recent years, the quality of speech synthesis based on end-to-end speech synthesis models has been ...
Qing-Dao-Er-Ji Ren +3 more
doaj +1 more source
Evaluating synthesized speech intelligibility in noise [PDF]
JASA Express LettersHumans can modify their speech to improve intelligibility in noisy environments. With the advancement of speech synthesis technology, machines may also synthesize voices that remain highly intelligible in noise condition.
Ye Yang +3 more
doaj +1 more source
Speech Synthesis of Arabic Vocabularies [PDF]
Al-Rafidain Journal of Computer Sciences and Mathematics, 2011 In this paper, system is presented for speech synthesis of Arabic vocabularies written with diacritics, graphemes transfer to allophones by applying the phonological rules.
Enaam Saeed
doaj +1 more source
Language-specific phonetic realisation of stop voicing contrasts in English and Japanese synthesised speech [PDF]
JASA Express LettersSpeech synthesis has improved dramatically over recent years, enabled by large datasets and advances in neural network architectures. Little is known, however, about how synthesised speech patterns are realized from a phonetic perspective.
James Tanner +2 more
doaj +1 more source
Croatian HMM-based Speech Synthesis
Journal of Computing and Information Technology, 2006 The paper describes the development of a trainable speech synthesis system, based on hidden Markov models. An approach to speech signal generation using a source-filter model is presented. Inputs into the synthesis system are speech utterances and their phone level transcriptions.
Martinčić-Ipšić, Sanda, Ipšić, Ivo
openaire +5 more sources
Using casual speech phonology in synthetic speech
Archives of Acoustics, 2014 Alphabetic writing is a mixed blessing for speech science. Most scientists working in speech synthesis and speech recognition assume unconsciously that spoken language is like written language, i.e.
Linda SHOCKEY
doaj
Alternative Speech Communication System for Persons with Severe Speech Disorders
EURASIP Journal on Advances in Signal Processing, 2009 Assistive speech-enabled systems are proposed to help both French and English speaking persons with various speech disorders. The proposed assistive systems use automatic speech recognition (ASR) and speech synthesis in order to enhance the quality of ...
Sid-Ahmed Selouani +2 more
doaj +1 more source
Lhasa-Tibetan Speech Synthesis Using End-to-End Model
IEEE Access, 2019 With the development of deep learning technology, speech synthesis based on deep neural networks has gradually become the mainstream method in the field of speech synthesis.
Yue Zhao +4 more
doaj +1 more source