Thu, Jan 23 PM 15:00 - 17:00 |
(1) |
15:00-15:30 |
Hearing Impairment Simulation using Audiogram-based Approximation of Auditory Filter and Loudness Compensation |
Nozomi Jimbo, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) |
(2) |
15:30-16:00 |
Fundamental study of speaker identification by the peripheral auditory model and deep neural network |
Masanori Morise, Kenji Ozawa (Univ. of Yamanashi) |
(3) |
16:00-16:30 |
Speaker recognition based on log-linear models using feature generation by variational Bayesian method |
Akifumi Tsuge, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) |
(4) |
16:30-17:00 |
A study on hyperparameter optimization for speech synthesis based on Gaussian process regression |
Tomoki Koriyama (Tokyo Inst. of Tech.), Takashi Nose (Tohoku Univ.), Takao Kobayashi (Tokyo Inst. of Tech.) |
Fri, Jan 24 AM 10:00 - 11:00 |
(5) |
10:00-10:30 |
Analysis of difference of temporal variation of spectrum due to tempo in scat including plural consonants |
Keisuke Tanizawa, Hideki Banno, Kensaku Asahi (Meijo Univ.) |
(6) |
10:30-11:00 |
A study on relationship between subjective individuality distance and vibrato-feature distance for vibrato singings |
Chifumi Suzuki, Hideki Banno, Kensaku Asahi (Meijo Univ.), Masanori Morise (Yamanashi Univ.) |
|
11:00-11:15 |
Break ( 15 min. ) |
Fri, Jan 24 AM 11:15 - 12:15 |
(7) |
11:15-12:15 |
[Invited Talk]
Bases and and recent challenges for analyzing multimodal interaction |
Katsuya Takanashi (Kyoto Univ) |
|
12:15-13:30 |
Lunch Break ( 75 min. ) |
Fri, Jan 24 PM 13:30 - 15:30 |
(8) |
13:30-14:00 |
Automatic Recogntion of Paralinguistic Information with Speaker Dependent Modeling |
Tomoyuki Shimakawa, Yoichi Yamashita (Ritsumeikan Univ.) |
(9) |
14:00-14:30 |
Contributing factors in preference judgement in read sentences using morphing of individual attributes |
Shoki Yoshimoto, Ryuichi Nisimura, Toshio Irino, Hideki Kawahara (Wakayama Univ) |
(10) |
14:30-15:00 |
A study of effective features for controlling the auditory impression based on voice morphing |
Masanori Morise, Satoshi Tsuzuki (Univ. of Yamanashi), Hideki Banno (Meijo Univ.), Kenji Ozawa (Univ. of Yamanashi) |
(11) |
15:00-15:30 |
Analysis of spectral characteristics in nasal for the purpose of improving voice quality of a speech analysis and synthesis system |
Shouhei Makino, Hideki Banno, Kensaku Asahi (Meijo Univ.) |