ACTOR: A multilingual unit-selection speech synthesis system
نویسندگان
چکیده
The ACTOR® Text-To-Speech (TTS) synthesis system, developed at Loquendo S.p.A., is here described. The system employs a unit -selection concatenative synthesis technique, relying on labeled acoustic databases providing phonetic and prosodic coverage of the intended language/domain and on an original algorithm for run-time selection of the acoustic units to be concatenated. This technique yields high -naturalness and human sounding voices. ACTOR® is a multi-voice and multi-language system, exploiting different kinds of language dependent knowledge (grammatical, phonetic and prosodic, as well as acoustic) with the support of several development tools (statistical tools for database design, machine learning algorithms, tools for speech signal analysis and phonetic alignment, etc.).
منابع مشابه
Study on Unit-Selection and Statistical Parametric Speech Synthesis Techniques
One of the interesting topics on multimedia domain is concerned with empowering computer in order to speech production. Speech synthesis is granting human abilities to the computer for speech production. Data-based approach and process-based approach are the two main approaches on speech synthesis. Each approach has its varied challenges. Unit-selection speech synthesis and statistical parametr...
متن کاملMultilingual Models in the Ibm Biling
In this paper we describe the role of multilingual models in the creation and deployment of unit selection based bilingual speech synthesizers. We first review the definition of a multilingual phonetic alphabet for the simultaneous recognition of up to fifteen languages, and then discuss synthesis specific modifications that allow a more detailed description of the synthesizers’ unit inventorie...
متن کاملHigh quality speech synthesis using a small speech dataset
We propose an approach to synthesizing high-quality speech under the conditions of a small dataset. A robust method for solving this problem is vital for voice restoration (recreation of lost fragments of records based on available speech material of a well-known person, e.g. an actor). The proposed TTS system is a hybrid system which includes the advantages of both HMMand Unit Selection-based ...
متن کاملAn embedded and concatenative approach to TTS of multiple languages
In thi and appro for E (Es.), efficie archit embe can b comm select text p the la are u letterspeec etc., a This paper presents an embedded and concatenative approach to multilingual text-to-speech system (ECMTTS). Under a uniform architecture, the TTS modules are separated into language dependent and independent ones. A specifically defined super phonetic symbol set enables to use uniform spee...
متن کاملAn Adaptable Acoustic Architecture in a Multilingual TTS System
In this paper an adaptable acoustical architecture in a multilingual TTS system is presented. The whole architecture is designed to be a data-driven system. Modules comprising text preprocessing, grapheme-to-phoneme conversion, lexical stress detection, OOV-handling, symbolic prosody prediction, acoustic prosody prediction and unit selection with concatenation use machine learning techniques es...
متن کامل