Abstract | ||
---|---|---|
This paper gives an overview of the design and development of an experimental restricted domain corpus-based unit selection text-to-speech (TTS) system for Hungarian The experimental system generates weather forecasts in Hungarian 5260 sentences were recorded creating a speech corpus containing 11 hours of continuous speech A Hungarian speech recognizer was applied to label speech sound boundaries Word boundaries were also marked automatically The unit selection follows a top-down hierarchical scheme using words and speech sounds as units A simple prosody model is used, based on the relative position of words within a prosodic phrase The quality of the system was compared to two earlier Hungarian TTS systems A subjective listening test was performed by 221 listeners The experimental system scored 3.92 on a five-point mean opinion score (MOS) scale The earlier unit concatenation TTS system scored 2.63, the formant synthesizer scored 1.24, and natural speech scored 4.86. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11846406_46 | TSD |
Keywords | Field | DocType |
corpus-based unit selection tts,experimental restricted domain,speech corpus,experimental system,speech sound boundary,earlier unit concatenation tts,hungarian tts system,continuous speech,corpus-based unit selection text-to-speech,natural speech,hungarian speech recognizer,weather forecasting,top down,mean opinion score | Speech corpus,Prosody,Speech synthesis,Computer science,Phrase,Mean opinion score,Speech recognition,Natural language,Natural language processing,Artificial intelligence,Formant,Sentence | Conference |
Volume | ISSN | ISBN |
4188 | 0302-9743 | 3-540-39090-1 |
Citations | PageRank | References |
5 | 0.47 | 3 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Márk Fék | 1 | 13 | 2.27 |
Péter Pesti | 2 | 5 | 0.47 |
Géza Németh | 3 | 102 | 25.57 |
Csaba Zainkó | 4 | 35 | 6.30 |
Gábor Olaszy | 5 | 50 | 13.40 |