Improvement of prosodic characteristic in Vietnamese speech synthesis system base on HMM
نویسنده
چکیده
The key factors helping people to understand the synthesized voices of text-to-speech system are the naturalness and the intelligibility. However, making more natural voices remains a difficult task because of the speech data’s scarcity. With data limited corpus, prosodic information such as tone, intonation, Part-of-Speech is added to ensure the quality of synthetic speech. In the paper, we investigate the effect of prosodic information on the naturalness of HMM-based synthesized voice when the available speech data is limited. The experimental result evaluated with objective measurement and MOS test showed that the intonation, POS tagging improve the naturalness of HMM-based synthesized voice.
منابع مشابه
HMM-based TTS for hanoi vietnamese: issues in design and evaluation
This paper presents the development and evaluation of an HMM-based TTS system for the modern Hanoi dialect of Northern Vietnamese, a tonal language. A study of specific phonetic and prosodic features of Hanoi Vietnamese is discussed. Consequences on the design of an HMM-based TTS system are derived. Using this knowledge, a TTS system, called VTed, is then developed under the Mary TTS platform. ...
متن کاملIntonation issues in HMM-based speech synthesis for Vietnamese
In an HMM-based Text-To-Speech system, contextual features, including phonetic and prosodic factors have a significant influence to the spectrum, F0 and duration of the synthetic voice. This paper proposes prosodic features aiming at improving the naturalness of an HMM-based TTS system (VTed) for a tonal language, Vietnamese. The ToBI (Tones and Break Indices) features are used to learn two cru...
متن کاملProsodic phrasing modeling for vietnamese TTS using syntactic information
This research aims at modeling prosodic phrasing for improving the naturalness of Vietnamese (a tonal language) speech synthesis. The proposed phrasing model includes hypotheses on: (i) prosodic structure based on syntactic rules (ii) final lengthening linked to syllabic structures and tone types. Audio files in the analysis corpus are manually transcribed at the syllable level and perceived pa...
متن کاملEvaluation of prosodic contextual factors for HMM-based speech synthesis
This paper explores the effect of prosodic contextual factors for speech synthesis based on hidden Markov model (HMM). In the HMM-based speech synthesis, to model not only the phonetic features but also the prosodic ones, a variety of contextual factors are taken into account in the model training. In a baseline system, a lot of contextual factors are used, and the resultant cost for parameter ...
متن کاملEvaluating Prosodic Characteristics for Vietnamese Airport Announcements
In most languages, the quality of a speech synthesis system relates directly to the diversity of language domain. Each domain, such as sports, entertainments, etc., has its specific grammar structures. The grammar structure plays as an important role for analyzing the prosodic information of utterances in each domain. In this research, we will analyze characteristics of prosodic information of ...
متن کامل