| Presentation | 2015-05-20 Continuous Inaudible Vowels Recognition Using Peaks of Lip Shape Transition based on Surface EMG Nao Kurogi, Hidetoshi Nagai, Teigo Nakamura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We research on inaudible speech recognition with surface EMGs. On a natural speech, we can't expect stability of characteristics while utterance of one vowel. So, in our previous works on continuous inaudible vowels recognition, we detected the phoneme boundaries and extracted features for recognition from the phoneme segment. However, influence of the previous or following phoneme weakens features of such a segment. We expect that we can get strong features of a vowel when speaker's lip shape is formed distinctly. In this paper, we show a method to detect the peaks of lip shape by tracking change of lip shape, and report the recognition result of continuous pair of inaudible vowels using the features around such peaks. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | inaudible speech recognition / silent speech recognition / wavelet analysis / surface EMG |
| Paper # | HCS2015-37,HIP2015-37 |
| Date of Issue | 2015-05-12 (HCS, HIP) |
| Conference Information | |
| Committee | HCS / HIP / HI-SIGCE |
|---|---|
| Conference Date | 2015/5/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Industry Support Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Communication Enhancing, Human Communications, and Human Information Processing |
| Chair | Kinya Fujita(Tokyo Univ. of Agric. and Tech.) / Hideyuki Ando(Osaka Univ.) |
| Vice Chair | Kyoko Ito(Osaka Univ.) / Masafumi Matsuda(NTT) / Masahiro Ishii(Sapporo City Univ.) / Miyuki Kamachi(Kogakuin Univ.) |
| Secretary | Kyoko Ito(Univ. of Tsukuba) / Masafumi Matsuda(Kanazawa Inst. of Tech.) / Masahiro Ishii(NICT) / Miyuki Kamachi(KDDI R&D Labs.) / (Nagoya Univ.) |
| Assistant | Yuugo Hayashi(Ritsumeikan Univ.) / Masashi Komori(Osaka Electro-Comm. Univ.) / Takahiro Tanaka(Nagoya Univ.) / Haruka Yoshida(NEC) / Sinobu Kuroki(NTT) / Mutsumi Suganuma(Waseda Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Human Communication Science / Technical Committee on Human Information Processing / Special Interest Group on Communication Enhancement |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Continuous Inaudible Vowels Recognition Using Peaks of Lip Shape Transition based on Surface EMG |
| Sub Title (in English) | |
| Keyword(1) | inaudible speech recognition |
| Keyword(2) | silent speech recognition |
| Keyword(3) | wavelet analysis |
| Keyword(4) | surface EMG |
| 1st Author's Name | Nao Kurogi |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 2nd Author's Name | Hidetoshi Nagai |
| 2nd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 3rd Author's Name | Teigo Nakamura |
| 3rd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| Date | 2015-05-20 |
| Paper # | HCS2015-37,HIP2015-37 |
| Volume (vol) | vol.115 |
| Number (no) | HCS-35,HIP-36 |
| Page | pp.pp.243-248(HCS), pp.243-248(HIP), |
| #Pages | 6 |
| Date of Issue | 2015-05-12 (HCS, HIP) |