Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 14:15 |
Tokyo |
|
An Open-Source Toolkit for Building Attractive Voice Interaction Systems -- MMDAgent Akinobu Lee, Keiichiro Oura, Keiichi Tokuda (Nitech) NLC2011-51 SP2011-96 |
The main and unique property of a spoken language interface that attracts people is the mutual, intuitive and lively int... [more] |
NLC2011-51 SP2011-96 pp.159-164 |
PRMU |
2011-11-25 13:45 |
Nagasaki |
|
Face recognition based on separable lattice 2-D HMMs with variational Bayesian method Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) PRMU2011-120 |
This paper proposes an image recognition technique based on separable lattice 2-D hidden Markov models (SL2D-HMMs) with ... [more] |
PRMU2011-120 pp.125-130 |
PRMU |
2011-11-25 14:15 |
Nagasaki |
|
Face recognition based on hidden conditional random fields using structure of separable lattice HMMs Keisuke Kumaki, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) PRMU2011-121 |
In image recognition, it needs to deal with geometrical variations of an object, e.g. location, size, and etc. Separable... [more] |
PRMU2011-121 pp.131-136 |
SP |
2011-06-23 15:30 |
Aichi |
Nagoya Univ. |
Bayesian speech recognition based on model structure integration Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) SP2011-32 |
This paper proposes an acoustic modeling technique using multiple model structures based on a Bayesian framework for spe... [more] |
SP2011-32 pp.11-16 |
SP |
2011-03-04 14:15 |
Tokyo |
Faculty of Engineering, The University of Tokyo |
Estimation of perceptual talker space using Japanese-English bilingual corpu Minoru Tsuzaki (Kyoto City Univ. of Arts), Keiichi Tokuda (Nagoya Inst. of Tech.), Hisashi Kawai, Jinfu Ni (NICT) SP2010-116 |
This paper reconfirms that talker identity can be transmitted even under the across-linguistic circumstances using a bil... [more] |
SP2010-116 pp.7-12 |
NLC, SP (Joint) [detail] |
2010-12-20 15:00 |
Tokyo |
National Olympics Memorial Youth Center |
Evaluation of spotting algorithm constrained by keyword co-occurrence for dialogue systems Aki Kato, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2010-16 SP2010-89 |
Question-answering dialogue system often choose a response sentence based on recognized keywords in a user's utterance. ... [more] |
NLC2010-16 SP2010-89 pp.25-30 |
NLC, SP (Joint) [detail] |
2010-12-21 11:05 |
Tokyo |
National Olympics Memorial Youth Center |
Evaluation of Successive Rapid Hypothesis Determination Algorithm for Continuous Word Recognition Hiroyuki Ohno (Nagoya Inst. of Tech.), Hiroshi Kojima (Nagoya Inst. of Tech/Hitachi Solutions, Ltd.), Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2010-21 SP2010-94 |
Minimizing response delay of speech recognition system and giving rapid feed backs are important properties for an intui... [more] |
NLC2010-21 SP2010-94 pp.77-82 |
PRMU, HIP |
2010-06-25 09:00 |
Aomori |
|
Face recognition based on extended separable lattice HMMs Keisuke Kumaki, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) PRMU2010-46 HIP2010-35 |
In image recognition systems, it needs to deal with geometrical variations of an object, e.g. location, size, rotation a... [more] |
PRMU2010-46 HIP2010-35 pp.45-50 |
SP, NLC |
2009-12-21 10:10 |
Tokyo |
Univ. of Tokyo |
Speaker Adaptation Using Nonlinear Spectral Transformation For Speech Recognition. Toyohiro Hayashi, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2009-12 SP2009-76 |
This paper proposes a speaker adaptation technique using nonlinear spectral transform based on GMMs.
One of the most po... [more] |
NLC2009-12 SP2009-76 pp.1-6 |
SP, NLC |
2009-12-22 09:55 |
Tokyo |
Univ. of Tokyo |
Voice activity detection using conditional random fields with multiple features Akira Saito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2009-18 SP2009-82 |
Voice Activity Detection (VAD) which is a technique to distinguish between speech and non-speech is used in noisy enviro... [more] |
NLC2009-18 SP2009-82 pp.59-64 |
SP, NLC |
2009-12-22 11:00 |
Tokyo |
Univ. of Tokyo |
Sentence generation from keywords using N-gram for Spoken Dialog System Yoshitaka Yoshimi, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2009-19 SP2009-83 |
A probabilistic answer selection on spoken dialog system requires a lot of question-and-answer pair as a training data. ... [more] |
NLC2009-19 SP2009-83 pp.71-76 |
SP, NLC |
2009-12-22 15:50 |
Tokyo |
Univ. of Tokyo |
Factor analysis models representing various voice characteristics for HMM based speech synthesis Kyosuke Kazumi, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2009-28 SP2009-92 |
This paper describes factor analysis models for realizing
various voice characteristics in the HMM-based speech synthe... [more] |
NLC2009-28 SP2009-92 pp.177-182 |
SP, NLC |
2009-12-22 15:50 |
Tokyo |
Univ. of Tokyo |
A speech-oriented information kiosk based on user-generated dialog contents Toshinori Fukuta, Yoshitaka Yoshimi, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2009-30 SP2009-94 |
On the development of a spoken dialog system, the system developer has to build and customize the contents for the targe... [more] |
NLC2009-30 SP2009-94 pp.207-212 |
PRMU |
2009-03-14 09:30 |
Miyagi |
Tohoku Institute of Technology |
Face recognition based on separable lattice 2-D HMM with state duration modeling Yoshiaki Takahashi, Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda (NIT) PRMU2008-262 |
This paper proposes separable lattice 2-D HMMs with state duration modeling.
Separable lattice 2-D HMMs(SL-HMMs) are pr... [more] |
PRMU2008-262 pp.153-158 |
PRMU |
2009-03-14 10:00 |
Miyagi |
Tohoku Institute of Technology |
Face recognition based on separable lattice 2-D HMM considering rotational variations Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda (NIT) PRMU2008-263 |
In image recognition systems,it needs to deal with geometrical variaions of
images such as size, location and rotaion.S... [more] |
PRMU2008-263 pp.159-164 |
SP |
2009-01-29 14:20 |
Nara |
NAIST |
Ultra-Rapid Speech Recognition based on Search Termination using Confidence Scoring Hiroshi Kojima, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) SP2008-128 |
In spite of the recent advances of speech recognition technology, a speech interface does not become a friendly, easy-to... [more] |
SP2008-128 pp.13-18 |
SP, NLC |
2008-12-10 09:55 |
Tokyo |
Waseda Univ. |
Bayesian Context Clustering Using Cross Validation for HMM-Based Speech Synthesis Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Institute of Technology) NLC2008-36 SP2008-91 |
This paper proposes a prior distribution determination technique using cross validation for HMM-based speech synthesis b... [more] |
NLC2008-36 SP2008-91 pp.73-78 |
SP, NLC |
2008-12-10 10:20 |
Tokyo |
Waseda Univ. |
Simultaneous Transformation of Duration and Spectrum Using Statistical Models Including Time-Sequence Matching Kaori Yutani, Yoshihiko Nankaku (Nagoya Institute of Technology), Tomoki Toda (Nara Institute of Science and Technology), Keiichi Tokuda (Nagoya Institute of Technology) NLC2008-37 SP2008-92 |
This paper describes a simultaneous conversion technique of duration and spectrum based on a statistical model including... [more] |
NLC2008-37 SP2008-92 pp.79-84 |
SP, NLC |
2008-12-10 16:10 |
Tokyo |
Waseda Univ. |
Speaker Recognition Based on Gaussian Mixture Models Using Variational Bayesian Method Tatsuya Ito, Kei Hashimoto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nitech) NLC2008-55 SP2008-110 |
[more] |
NLC2008-55 SP2008-110 pp.185-190 |
SP, NLC |
2008-12-10 16:10 |
Tokyo |
Waseda Univ. |
Tying covariance parameters for HMM-based speech synthesis Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inusitute of Technology) NLC2008-60 SP2008-115 |
In this paper, we proposed a tying covariance technique in hidden Markov model (HMM) basedspeech
synthesis system. In r... [more] |
NLC2008-60 SP2008-115 pp.215-220 |