Rule-Based Performative Synthesis of Sung Syllables
نویسندگان
چکیده
In this demonstration, the mapping and the gestural control strategy developed in the Digitartic are presented. Digitartic is a musical instrument able to control sung syllables. Performative rule-based synthesis allows for controlling semi-consonants, plosive, fricative and nasal consonants with a same gesture, despite the structural differences in natural production of such vocal segments. A graphic pen tablet is used for capturing the gesture with a high sampling rate and resolution. This system allows for both performing various manners of articulation and having continuous control over the articulation.
منابع مشابه
Vokinesis: syllabic control points for performative singing synthesis
Performative control of voice is the process of real-time speech synthesis or modification by the means of hands or feet gestures. Vokinesis, a system for real-time rhythm and pitch modification and control of singing is presented. Pitch and vocal effort are controlled by a stylus on a graphic tablet. The concept of Syllabic Control Points (SCP) is introduced for timing and rhythm control. A ch...
متن کاملModeling of geminate duration in an amharic text-to-speech synthesis system
This paper presents analysis and modeling of geminate duration in Amharic Text-to-Speech (AmhTTS) synthesis system. AmhTTS is a parametric and rule-based system that employs a cepstral method. The system uses a source filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. Fundamental speech units of the system are syllables. Gemination in Am...
متن کاملA Romanian Syllable-Based Text-To-Speech System
In this article we present the way we have built a syllable-based TTS system for Romanian. The system contains: a text analyser capable to separate syllables from input text and detect accentuation, a vocal database with recorded syllables, a unit matching module and a synthesizer. The analyser was built using a LEX generator by mean of two sets of phonetic rules. Vocal database was generated t...
متن کاملProsody annotation for corpus based speech synthesis
The paper concerns prosody annotation especially for application in a corpus based speech synthesis. In order to establish the rules of automatic intonation modelling, phonetically labeled speech database of 4 hours has been perceptually and acoustically analyzed. The speech material included different text types and prosodically rich phrases. The annotation of the speech database consists in p...
متن کاملAutomatic Prosodic Break Lab Chinese Speech
For corpus-based speech synthesis, large quantities of labeled speech are required. Manually labeling speech data is quite laborintensive. Therefore, automatic speech labeling is highly desired. Prosodic break detection is one of the tasks for automatic speech labeling. In the paper, we propose an automatic break detection algorithm for mandarin Chinese speech. In this approach, we use energy c...
متن کامل