Information and Systems-Natural Language Understanding and Models of Communication(Date:2015/12/02)

Automation of high performance system building for large vocabulary speech recognition using evolution strategy with pareto optimality

Takafumi Moriya(Tokyo Tech),  Tomohiro Tanaka(Tokyo Tech),  Takahiro Shinozaki(Tokyo Tech),  Shinji Watanabe(MERL),  Kevin Duh(NAIST),  

[Paper #]SP2015-75
Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine

Toru Nakashika(UEC),  Tetsuya Takiguchi(Kobe Univ.),  

[Paper #]SP2015-71
Investigation of DNN Based Distant-Talking Speech Enhancement

Zeyan Oo(NUT),  Longbiao Wang(NUT),  Masahiro Iwahashi(NUT),  

[Paper #]SP2015-76
Distant-talking speech recognition by reverberation-aware denoising autoencoder

Yuma Ueda(Shizuoka Univ.),  Longbiao Wang(Nagaoka Univ.),  Atsuhiko Kai(Shizuoka Univ.),  

[Paper #]SP2015-77
Parallel Dictionary Learning for Voice Conversion Using Alternating Direction Method of Multipliers

Ryo Aihara(Kobe Univ.),  Tetsuya Takiguchi(Kobe Univ.),  Yasuo Ariki(Kobe Univ.),  

[Paper #]SP2015-72
Evaluation of estimation accuracy of vocal tract shape by using FDTD simulation in extraction method of vocal tract area function

Takaaki Kondo(Meijo Univ.),  Hideki Banno(Meijo Univ.),  Kensaku Asahi(Meijo Univ.),  

[Paper #]SP2015-78
An analysis of difference among singers in kurtosis of LPC residual spectrum of breathy vowel voice

Masahiro Itou(Meijo Univ.),  Hideki Banno(Meijo Univ.),  Kensaku Asahi(Meijo Univ.),  

[Paper #]SP2015-79
Evaluation and Analysis of Duration Correction for Non-Native Speech Based on Waveform Modification

Shinya Kura(NAIST),  Shinnosuke Takamichi(NAIST),  Tomoki Toda(NAIST/Nagoya Univ.),  Graham Neubig(NAIST),  Sakriani Sakti(NAIST),  Satoshi Nakamura(NAIST),  

[Paper #]SP2015-73
Voice Conversion based on Projection to Speaker Space Bases constructed by Deep Neural Network

Tetsuya Hashimoto(UTokyo),  Yosuke Kashiwagi(UTokyo),  Daisuke Saito(UTokyo),  Minematsu Nobuaki(UTokyo),  

[Paper #]SP2015-70
[Invited Talk] When will computer speech technologies exceed human abilities ?

Seiichi Nakagawa(TUT),  

[Paper #]SP2015-74
Deep Auto-encoder based Low-dimensional Feature Extraction using FFT Spectral Envelopes in Statistical Parametric Speech Synthesis

Shinji Takaki(NII),  Junichi Yamagishi(NII),  

[Paper #]SP2015-81
Evaluation of text-to-speech system construction for unknown-pronunciation languages

Kei Sawada(Nagoya Inst. of Tech.),  Kei Hashimoto(Nagoya Inst. of Tech.),  Keiichiro Oura(Nagoya Inst. of Tech.),  Yoshihiko Nankaku(Nagoya Inst. of Tech.),  Keiichi Tokuda(Nagoya Inst. of Tech.),  

[Paper #]SP2015-80
[Poster Presentation] Extracting Relationship of Meeting Minutes Generated By Speech Recognition System based on phonemes

Motoki Ito(Takushoku Univ.),  Seikoh Nishita(Takushoku Univ.),  

[Paper #]NLC2015-34
Multi-speaker speech synthesis and speaker adaptation based on deep bidirectional long short-term memory recurrent neural network

Yi Zhao(UTokyo),  Nobuaki Minematsu(UTokyo),  Daisuke Saito(UTokyo),  

[Paper #]SP2015-82
[Poster Presentation] Harnessing Chat Logs and User Profiles for Recurrent Neural Network Based Casual Conversation Generation

Mitsuharu Makita(CyberAgent),  Roman Shtykh(CyberAgent),  

[Paper #]NLC2015-35
Unsupervised Sentence Compression of Speech Recognition Results Dealing with Speech Recognition Error

Takaaki Sato(NTT),  Takanobu Oba(NTT docomo),  Hirokazu Masataki(NTT),  Yushi Aono(NTT),  

[Paper #]SP2015-84
Analyzing the human-human dialog and examining to build WOZ system for estimating the user's willingness to talk

Yuya Chiba(Tohoku Univ.),  Akinori Ito(Tohoku Univ.),  

[Paper #]SP2015-83
Detection of Mathematical Formula Regions in Images of Scientific Papers by using Deep Learning and OCR

Shintaro Date(Okayama Pref. Univ.),  Hideki Isozaki(Okayama Pref. Univ.),  

[Paper #]NLC2015-37
[Poster Presentation] A Study of Semantic Role Labels for Annotating Predicate-Argument Structure Thesaurus to BCCWJ

Koichi Takeuchi(Okayama Univ.),  

[Paper #]NLC2015-36
[Invited Talk] Statistical speech synthesis: past, present and future

Keiichi Tokuda(NITECH),  

[Paper #]
12>> 1-20hit(26hit)