From MBROLA to NU-MBROLA
نویسندگان
چکیده
We introduce the NU-MBROLA project as an extension of the MBROLA project for designing large NU-MBROLA databases exhibiting the same properties as MBROLA diphone databases, without the restriction of being composed of diphones. The accompanying NU-MBROLA synthesizer implements the MBROLA algorithm on speech segments only defined by their starting and ending points in natural speech files. It is distributed with the same terms and conditions as in the MBROLA project. The terms and conditions for the creation of NU-MBROLA database are slightly different from those related to the creation of MBROLA databases, mainly in that no speech segmentation is required, and in that we leave it to providers to distribute their NU-MBROLA databases.
منابع مشابه
Improving quality in a speech synthesizer based on the MBROLA algorithm
Speech synthesis based on the Multiband Resynthesis OverLap-Add (MBROLA) algorithm produces high quality speech without requiring too much effort to design the diphone database, and using a low computational power. The main drawback of this algorithm is the slightly metallic sound or buzziness that can be perceived on voiced segments. We are working on a speech synthesizer based on the MBROLA a...
متن کاملA simple and efficient algorithm for the compression of MBROLA segment databases
Most state-of-the-art TTS synthesizers are based on a technique known as synthesis by concatenation, in which speech is produced by concatenating elementary speech units. The design of a high-quality TTS system implies the storage of a large number of segments. To facilitate the storage of these segments, this paper proposes a very low complexity coder to compress unit databases with a toll qua...
متن کاملThe MBROLA project: towards a set of high quality speech synthesizers free of use for non commercial purposes
The aim of the MBROLA project, recently initiated by the Faculté Polytechnique de Mons (Belgium), is to obtain a set of speech synthesizers for as many voices, languages and dialects as possible, free of use for non-commercial and non-military applications. The ultimate goal is to boost up academic research on speech synthesis, and particularly on prosody generation, known as one of the biggest...
متن کاملEfficient Diphone Database Creation for MBROLA, a Multilingual Speech Synthesiser
Diphone synthesis is a convenient way for testing phonetic models of human speech. It allows easy manipulation of duration and pitch, therefore it is used not only for general intonation contour evaluation, but also for expressive speech synthesis. The main advantage of using MBROLA [11][9],[12],[13] is the fact that not all the diphones need to be contained in the voice to test speech models. ...
متن کاملAn Overview of Speech Recognition and Speech Synthesis Algorithms
This paper describes about some speech synthesis and speech recognition algorithms and compares their performance based on accuracy and quality. In speech recognition DTW and HMM algorithms are compared with respect to accuracy. Comparative study of CELP and MBROLA algorithm of speech synthesis based on quality is also done.
متن کامل