2001 · 51 citations · 5 references
Language StudiesLinguisticsImprovisationPhoneticsVocal PerformanceSpeech RecognitionSpeech Sound ProductionSpeech SynthesisVoice GenerationIntonation Modeling
The paper describes developing the first Italian version of the Festival TTS system. The authors implemented Italian voices using three engines—Festival residual LPC, OGI residual LPC plug‑in, and MBROLA—with male and female voices. Festival now supports Italian, and the voices and modules are freely downloadable for non‑commercial use. The paper is dedicated to the memory of Mike Macon.
Finally Festival speaks Italian. In this work, the development of the first Italian version of the Festival TTS system is described. One male and one female voice for three different speech engines are considered: the Festival-specific residual LPC synthesizer, the OGI residual LPC Plug-In for Festival and the MBROLA synthesizer. The new Italian voices will be freely available for download for non-commercial purposes together with specific software modules at http://nts.csrf.pd.cnr.it/IFD/Pages/Italian-TTS.htm. This paper is devotedly dedicated to the memory of Mike Macon, whose recent passing on was really a shock to all of his friends.
5
A baseline of a speaker independent continuous speech recognizer of Italian
B. Angelini, Fabio Brugnara, Daniele Falavigna et al. · 1993 · 12 citations