| P98-1111 | have been made for high-quality | textto-speech | systems ( van Santen et al. , |
| A94-1047 | speech techniques or commercial | textto-speech | output devices suffer from a |
| D13-1165 | normalization has been a major focus in | textto-speech | ( TTS ) research for many years |
| P94-1013 | problem of homograph resolution in | textto-speech | synthesis . The algorithm achieved |
| P06-2125 | phrasing is essential to Mandarin | textto-speech | synthesis . We select word format |
| P86-1022 | produce something that will further | textto-speech | technology . SYNTACTIC STRUCTURE |
| N13-1023 | real-time S2S translation as the | textto-speech | synthesis is monotonic and can |
| P89-1000 | research . The presentation on | textto-speech | synthesis will cover current |
| J97-4001 | get a more natural prosodics in | textto-speech | synthesizers . The same formalism |
| P06-1140 | prediction , compared to unrestricted | textto-speech | synthesis . While this topic |
| P98-2147 | Sproat , 1996 ) that is used in | textto-speech | projects at Lucent Bell Laboratories |
| W01-1610 | at AT&T , combining ASR and | textto-speech | with a phone interface ( Kamm |
| A97-1018 | , OCR , speech recognition and | textto-speech | conversion systems . For instance |
| D09-1096 | component in a system for email | textto-speech | rendering . The authors claim |
| P86-1022 | distinguished , using the current | textto-speech | system annotations . Prosodic |
| P13-1114 | need for normalization as part of | textto-speech | systems ( Beaufort et al. , 2010 |
| E03-2011 | Automatic Speech Recognition and | Textto-Speech | engines and Semantic Parsers |
| P98-2129 | automatic speech recognition ( ASR ) , | textto-speech | ( TTS ) , a phone interface , |
| P00-1021 | is realised with off-the-shelf | textto-speech | software ( Fujitsu 's Japanese |
| J98-4010 | recent book ( An Introduction to | Textto-Speech | Synthesis -LSB- 1997 -RSB- , |
