Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP, NLC |
2008-12-10 16:10 |
Tokyo |
Waseda Univ. |
Dialect-based speaker classification of Chinese using acoustic features invariant with extra-linguistic factors XueBin Ma, Nobuaki Minematsu, Yu Qiao, Keikichi Hirose (Univ. of Tokyo), Akira Nemoto (Nankai Univ.), Feng Shi (nankai Univ.) NLC2008-54 SP2008-109 |
Chinese dialects-based speaker classification using modern speech technologies is really a challenge, not only because t... [more] |
NLC2008-54 SP2008-109 pp.179-184 |
SP, NLC |
2008-12-10 16:10 |
Tokyo |
Waseda Univ. |
Isolated word recognition based on speech structures and discriminant analysis Satoshi Asakawa, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) NLC2008-58 SP2008-113 |
Non-linguistic factors of speech such as vocal tract sizes and recording devices easily change
acoustic features of spe... [more] |
NLC2008-58 SP2008-113 pp.203-208 |
SP, NLC |
2008-12-10 16:10 |
Tokyo |
Waseda Univ. |
Speech recognition using localized affine invariant features Masayuki Suzuki, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) NLC2008-59 SP2008-114 |
This paper proposes localized affine invariant features (LAIFs) for speaker-independent automatic speech recognition. Th... [more] |
NLC2008-59 SP2008-114 pp.209-214 |
SP |
2008-11-20 17:15 |
Gifu |
Softopia Japan (Ogaki) |
Development of a speech generator from hand motions based on space mapping Aki Kunikoshi, Yu Qiao, Masayuki Suzuki, Nobuaki Minematsu, Keikichi Hirose (Tokyo Univ.) SP2008-78 |
When individuals with speaking disabilities, dysarthrics, want to communicate using speech, they often use speech synthe... [more] |
SP2008-78 pp.45-50 |
SP |
2008-10-23 15:15 |
Kumamoto |
Kumamoto Univ. |
[Invited Talk]
Speech Prosody in Spoken Language Processing Keikichi Hirose (The Univ. of Tokyo) SP2008-60 |
Prosodic features of speech are known to play an important role in the transmission of linguistic information in human c... [more] |
SP2008-60 pp.25-30 |
SP |
2008-07-17 - 2008-07-19 |
Iwate |
Iwate Prefectural Univ. |
Parameter sharing and its effects for structural speech recognition Ryo Matsuura, Daisuke Saito, Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hirose (Tokyo Univ.) SP2008-52 |
Acoustic features in speech are affected inevitably by non-linguistic factors, which easily decrease speech recognition ... [more] |
SP2008-52 pp.55-60 |
SP |
2008-06-27 - 2008-06-28 |
Hokkaido |
|
Experimental Study of Using Spectrum-based Features for Structural Representation of Speech Masayuki Suzuki, Satoshi Asakawa, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2008-32 |
Non-linguistic factors such as morphological differences in vocal tracts inevitably affect acoustic features of speech. ... [more] |
SP2008-32 pp.73-78 |
SP |
2008-06-27 - 2008-06-28 |
Hokkaido |
|
A Study on Automatic Scoring Methods for Language Learners' Shadowing Productions Dean Luo, Naoya Shimomura, Nobuaki Minematsu (The Univ. of Tokyo), Yutaka Yamauchi (Tokyo International Univ.), Keikichi Hirose (The Univ. of Tokyo) SP2008-29 |
Shadowing has been used as a method for improving speaking and listening ability that requires learners to repeat, or sh... [more] |
SP2008-29 pp.55-60 |
SP |
2008-06-27 - 2008-06-28 |
Hokkaido |
|
Proposal of structure-to-speech conversion and its application to implementation of infants' vocal imitation Daisuke Saito, Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2008-40 |
Speech acoustics vary due to differences in age, gender, vocal tract length, microphone, and so on. The authors recently... [more] |
SP2008-40 pp.115-120 |
SP |
2008-06-27 - 2008-06-28 |
Hokkaido |
|
F0 features of Japanese Sentences Read Aloud by English, Chinese, and Naive speakers. Hiroko Hirano, Keikichi Hirose (Univ. of Tokyo), Goh Kawai (Hokkaido Univ.), Nobuaki Minematsu (Univ. of Tokyo) SP2008-27 |
(To be available after the conference date) [more] |
SP2008-27 pp.43-48 |
SP |
2008-03-21 15:45 |
Tokyo |
Univ. Tokyo |
Automatic scoring of language learners' utterances generated through shadowing based on bottom-up clustering Naoya Shimomura, Nobuaki Minematsu (Univ. of Tokyo), Yutaka Yamauchi (Tokyo International Univ.), Keikichi Hirose (Univ. of Tokyo) SP2007-212 |
Recently, shadowing has attracted much attention in the field of teaching and learning foreign languages.
Shadowing is... [more] |
SP2007-212 pp.151-156 |
SP |
2007-10-25 - 2007-10-26 |
Nagasaki |
Nagasaki University |
Two-step generation of F0 fundamental frequency contours of Chinese and its use for realizing flexible control of prosody Qinghua Sun, Keikichi Hirose, Nobuaki Minematsu (Univ. of Tokyo) SP2007-77 |
[more] |
SP2007-77 pp.37-42 |
SP |
2007-10-25 - 2007-10-26 |
Nagasaki |
Nagasaki University |
Copus-based generation of prosodic features using the generation model of fundamental frequancy contours Keiko Ochi, Keikichi Hirose, Nobuaki Minematsu (Tokyo Univ.) SP2007-78 |
[more] |
SP2007-78 pp.43-48 |
SP |
2007-10-25 - 2007-10-26 |
Nagasaki |
Nagasaki University |
A fundamental study of structure-to-speech conversion Daisuke Saito, Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hirose (The Univ. of Tokyo) SP2007-80 |
Speech acoustics vary due to differences in age, gender, vocal tract length, microphone, and so on. The authors recently... [more] |
SP2007-80 pp.55-60 |
SP |
|
Toyama |
Toyama Prefectural University |
Automatic estimation of the vowel correction priority for language learners based on the structural representation of pronunciation Kei Kamata, Satoshi Asakawa, Nobuaki Minematsu (Univ. of Tokyo), Takehiko Makino (Chuo Univ.), Keikichi Hirose (Univ. of Tokyo) SP2007-36 |
Speech communication induces inevitable variations of speech acoustics due to differences in speakers, microphones, etc.... [more] |
SP2007-36 pp.73-78 |
SP |
2007-06-28 15:15 |
Fukushima |
The University of Aizu |
Detection of acoustic event boundaries from continuous speech based on constrained clustering Naoya Shimomura, Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2007-12 |
Speech databases with accurate phoneme labeling are often required to improve speech technologies. Although HMM-based fo... [more] |
SP2007-12 pp.25-30 |