IEICE Technical Report

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

Speech

Workshop Date : 2015-12-02 - 2015-12-03 / Issue Date : 2015-11-25

SP2015-70
Voice Conversion based on Projection to Speaker Space Bases constructed by Deep Neural Network
Tetsuya Hashimoto, Yosuke Kashiwagi, Daisuke Saito, Minematsu Nobuaki (UTokyo)
pp. 1 - 6

SP2015-71
Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine
Toru Nakashika (UEC), Tetsuya Takiguchi (Kobe Univ.)
pp. 7 - 12

SP2015-72
Parallel Dictionary Learning for Voice Conversion Using Alternating Direction Method of Multipliers
Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.)
pp. 13 - 18

SP2015-73
Evaluation and Analysis of Duration Correction for Non-Native Speech Based on Waveform Modification
Shinya Kura, Shinnosuke Takamichi (NAIST), Tomoki Toda (NAIST/Nagoya Univ.), Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST)
pp. 19 - 24

SP2015-74
[Invited Talk] When will computer speech technologies exceed human abilities ?
Seiichi Nakagawa (TUT)
pp. 25 - 30

SP2015-75
Automation of high performance system building for large vocabulary speech recognition using evolution strategy with pareto optimality
Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki (Tokyo Tech), Shinji Watanabe (MERL), Kevin Duh (NAIST)
pp. 31 - 36

SP2015-76
Investigation of DNN Based Distant-Talking Speech Enhancement
Zeyan Oo, Longbiao Wang, Masahiro Iwahashi (NUT)
pp. 37 - 42

SP2015-77
Distant-talking speech recognition by reverberation-aware denoising autoencoder
Yuma Ueda (Shizuoka Univ.), Longbiao Wang (Nagaoka Univ.), Atsuhiko Kai (Shizuoka Univ.)
pp. 55 - 60

SP2015-78
Evaluation of estimation accuracy of vocal tract shape by using FDTD simulation in extraction method of vocal tract area function
Takaaki Kondo, Hideki Banno, Kensaku Asahi (Meijo Univ.)
pp. 61 - 63

SP2015-79
An analysis of difference among singers in kurtosis of LPC residual spectrum of breathy vowel voice
Masahiro Itou, Hideki Banno, Kensaku Asahi (Meijo Univ.)
pp. 65 - 69

SP2015-80
Evaluation of text-to-speech system construction for unknown-pronunciation languages
Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.)
pp. 93 - 98

SP2015-81
Deep Auto-encoder based Low-dimensional Feature Extraction using FFT Spectral Envelopes in Statistical Parametric Speech Synthesis
Shinji Takaki, Junichi Yamagishi (NII)
pp. 99 - 104

SP2015-82
Multi-speaker speech synthesis and speaker adaptation based on deep bidirectional long short-term memory recurrent neural network
Yi Zhao, Nobuaki Minematsu, Daisuke Saito (UTokyo)
pp. 105 - 110

SP2015-83
Analyzing the human-human dialog and examining to build WOZ system for estimating the user's willingness to talk
Yuya Chiba, Akinori Ito (Tohoku Univ.)
pp. 117 - 122

SP2015-84
Unsupervised Sentence Compression of Speech Recognition Results Dealing with Speech Recognition Error
Takaaki Sato (NTT), Takanobu Oba (NTT docomo), Hirokazu Masataki, Yushi Aono (NTT)
pp. 123 - 127

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