IEICE Technical Report

Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380

Speech

Workshop Date : 2014-07-24 - 2014-07-26 / Issue Date : 2014-07-17

SP2014-63
Investigation of Combining Multiple Language Modeling Techniques in Japanese Spontaneous Speech Recognition
Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi (NTT)
pp. 1 - 6

SP2014-64
Speaker Change Detection using Mel Logarithm Power-Cepstrum and MFCC
Masashi Tateno, Eiji Kamioka (Shibaura Inst. of Tech.)
pp. 7 - 12

SP2014-65
A generalized discriminative training framework for system combination
Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John Hershey (Mitsubishi Electric)
pp. 13 - 18

SP2014-66
[Invited Talk] Voice conversion based on sparse representation and its application to articulation disorders
Tetsuya Takiguchi (Kobe Univ.)
pp. 19 - 24

SP2014-67
[Invited Talk] Speech research as a problem of statistical machine learning
Yoshihiko Nankaku (Nagoya Inst. of Tech.)
pp. 25 - 30

SP2014-68
[Invited Talk] Evaluation Criteria of Statistical Learning when Gaussian Approximation can not be Applied to Likelihood Function
Sumio Watanabe (Tokyo Inst. of Tech.)
pp. 31 - 36

SP2014-69
[Invited Talk] Karnel method for Bayesian inference and its applications
Kenji Fukumizu (ISM)
pp. 37 - 40

SP2014-70
Phonetical Restoring Effect meaning Reinforcement Learning with QAM -- For the acoustic communication which is robust for Jitter --
Kazuhide Okada (COM, FS)
pp. 41 - 46

SP2014-71
Dialogue group detection and speaker diarization for multi-party conversational speech recorded by multiple smartphones
Koji Iwano, Toko Iizuka, Kanoko Saito, Shuhei Yoneyama (Tokyo City Univ.)
pp. 47 - 52

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan