| Presentation | 2015-10-04 An N-gram-based approach for input text synthesis depending on text-to-speech system Wang Le, Kacper Radzikowski, Yoshie Osamu, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Plenty of researches on text-to-speech(TTS) system have been made, in which prosodic information plays an important role. Most of the works focuses on how to get high quality speech from right sentence. As an actual situation, however, it sometimes the case that TTS system is given and we cannot increase its performance. Under such situation input sentence generation, even though it contains incorrect expression, is an interesting idea, so that we can get right phoneme and accent. Using N-gram model we propose such a method, where the most plausible interpretation (segmentation) of the given sequence of phoneme and accent is searched. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | N-gram / Text-to-speech / Text synthesis / Accent phrase |
| Paper # | TL2015-34 |
| Date of Issue | 2015-09-27 (TL) |
| Conference Information | |
| Committee | TL |
|---|---|
| Conference Date | 2015/10/4(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | WASEDA University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | resource, language and learning, co-creation in a place, thought and language, etc. |
| Chair | Tadahisa Kondo(Kogakuin Univ.) |
| Vice Chair | Chiaki Kubomura(Yamano College of Aesthetics) / Masami Suzuki(KDDI R&D Labs.) |
| Secretary | Chiaki Kubomura(Univ. of Tsukuba) / Masami Suzuki(Kyorin Univ.) |
| Assistant | Eiji Tomida(Ehime Univ.) / Yasushi Tsubota(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Thought and Language |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | An N-gram-based approach for input text synthesis depending on text-to-speech system |
| Sub Title (in English) | |
| Keyword(1) | N-gram |
| Keyword(2) | Text-to-speech |
| Keyword(3) | Text synthesis |
| Keyword(4) | Accent phrase |
| 1st Author's Name | Wang Le |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Kacper Radzikowski |
| 2nd Author's Affiliation | Waseda University(Waseda Univ.) |
| 3rd Author's Name | Yoshie Osamu |
| 3rd Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2015-10-04 |
| Paper # | TL2015-34 |
| Volume (vol) | vol.115 |
| Number (no) | TL-238 |
| Page | pp.pp.1-5(TL), |
| #Pages | 5 |
| Date of Issue | 2015-09-27 (TL) |