[TOP] | [2006] | [2007] | [2008] | [2009] | [2010] | [2011] | [2012] | [Japanese] / [English]
[PROGRAM] [BULK PDF DOWNLOAD]
SP2007-24
Examination of criterion to distinguish between normal and unusual articulation
Akikazu Nishikido, Jianwu Dang (JAIST)
pp. 1 - 6
SP2007-25
A Flexible Temporal Decomposition-based Spectral Modification Method using Asymmetric Gaussian Mixture Model
Binh Phu Nguyen, Masato Akagi (JAIST)
pp. 7 - 12
SP2007-26
A temporal and frequency interference-free power spectral representation of periodic signals
-- Toward STRAIGHT spectral estimation without tunable component --
Hideki Kawahara, Masanori Morise, Toru Takahashi, Ryuichi Nisimura, Toshio Irino (Wakayama Univ.), Hideki Banno (Meijo Univ.)
pp. 13 - 18
SP2007-27
Improvement in detectability of alarm signals in noisy environments by utilizing spatial cues
Hideaki Uchiyama, Masashi Unoki, Masato Akagi (JAIST)
pp. 19 - 24
SP2007-28
Physical characteristics of earphone for psychoacoustic experiment
Hiroki Aoyama, Makoto Otani, Tatsuya Hirahara (Toyama Pref. Univ.)
pp. 25 - 30
SP2007-29
Neural mechanisms of auditory awareness involved in perceptual transitions
Hirohito M. Kondo, Makio Kashino (NTT Commun Sci Labs)
pp. 31 - 36
SP2007-30
Is the ability of identifying a given [a] sound as phoneme /a/ necessary for spoken language competence?
Nobuaki Minematsu, Tazuko Nishimura (Univ. of Tokyo), Kyoko Sakuraba (Kiyose Welfare Center), Satoshi Asakawa, Daisuke Saito (Univ. of Tokyo)
pp. 37 - 42
SP2007-31
Role of Articulatory Gesture in Acquisition Process of Infants Vowel Imitation
Takeshi Konno, Akikazu Nishikido, Jianwu Dang (JAIST)
pp. 43 - 48
SP2007-32
A Study on Expressive Speech and Perception of Semantic Primitives: Comparison between Taiwanese and Japanese
Chun-Fang Huang (JAIST), Donna Erickson (Showa Music Univ.), Masato Akagi (JAIST)
pp. 49 - 54
SP2007-33
On Noise Robustness of Feature Expressing Temporal Variation for Word Speech Recognition
Tetsuo Funada, Megumi Umeno, Hideyuki Nomura (Kanazawa Univ.)
pp. 55 - 60
SP2007-34
An application of feature FTTSS to telephone speech recognition
Masafumi Mikuni, Tetsuo Funada, Hideyuki Nomura (Kanazawa Univ.)
pp. 61 - 66
SP2007-35
Acoustic Modeling Based on Model Structure Annealing for Speech Recognition
Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nitech)
pp. 67 - 72
SP2007-36
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)
pp. 73 - 78
SP2007-37
Evaluation of speaker verification with NAM segments using unknown speakers
Hideki Okamoto, Mariko Kojima (NAIST), Tomoko Matsui (ISM), Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST)
pp. 79 - 84
SP2007-38
Acoustic characteristics of Non-Audible Murmur and NAM Microphone Response
Shota Shimizu, Makoto Otani, Tatsuya Hirahara (Toyama Pref. Univ.)
pp. 85 - 90
SP2007-39
Comparison of Small Sound Source Signals in the Speech Communication-Aid System for Laryngectomees
Keigo Nakamura, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST)
pp. 91 - 96
SP2007-40
Construction and preliminary analysis of a large-scale bone-conducted speech database
Hisanori Makinae, Takashi Osanai, Toshiaki Kamada, Masumi Tanimoto (NRIPS)
pp. 97 - 102
SP2007-41
Evaluations of an LP-based blind restoration method to improve intelligibility of BC speech
Masashi Unoki, Vu tat Thang, Germine Seide, Masato Akagi (JAIST)
pp. 103 - 108
SP2007-42
A Speech Enhancement Framework Based on Noise Eigenspace Projection
Dongwen Ying, Masashi Unoki, Jianwu Dang (JAIST)
pp. 109 - 114
SP2007-43
A numerical simulation of pathological speech production based on asymmetric vocal folds model
Hideyuki Nomura, Tetsuo Funada (Kanazawa Univ.)
pp. 115 - 120
SP2007-44
Normalization of Vocal Tract Shape Using a Radial Basis Function
Jianguo Wei, Xugang Lu, Qiang Fang, Jianwu Dang (JAIST)
pp. 121 - 126
Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.