Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP |
2009-01-29 13:30 |
Nara |
NAIST |
Automatic Reading Annotation to Trendy Keywords by Web Text Mining focused on Parentheses Expression Jumpei Miyake, Shota Takeuchi, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano (Nara Inst. of Scie and Tech.) SP2008-126 |
In this paper, we propose a novel method to automatically annotate readings (kana, furigana)
to Japanese trendy words ... [more] |
SP2008-126 pp.1-6 |
SP |
2009-01-29 13:55 |
Nara |
NAIST |
Error Detection in Speech Recognition using CRF Based on Various Linguistic Features Tomohiko Matsumoto, Atsushi Sako, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2008-127 |
Recently, a learning method of n-gram showing error tendency is focused on. In this method, it is difficult to learn low... [more] |
SP2008-127 pp.7-12 |
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 |
2009-01-29 14:45 |
Nara |
NAIST |
Speeding up fundamental frequency information extraction by Hough transform for noise-rubust speech recognition Hideki Yasui, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.), Koji Iwano (Musashi Inst. of Tech.) SP2008-129 |
While $F_0$ information obtained by Hough transform has been shown to be effective in speech recognition in noisy enviro... [more] |
SP2008-129 pp.19-24 |
SP |
2009-01-29 15:10 |
Nara |
NAIST |
WFST-based Dialog Management Using Statistical Dialog Model Chiori Hori, Kiyonori Ohtake, Teruhisa Misu, Hideki Kashioka, Satoshi Nakamura (NICT-ATR) SP2008-130 |
Abstract We have proposed an expandable and portable dialog scenario description and platform to manage dialog sys-tems... [more] |
SP2008-130 pp.25-30 |
SP |
2009-01-29 15:50 |
Nara |
NAIST |
[Invited Talk]
State of the art Speech Translation Technologies Satoshi Nakamura (NICT/ATR) SP2008-131 |
Speech Translation Research launched in 1986 at ATR has finally realized a world-first mobile phone-based speech transla... [more] |
SP2008-131 pp.31-36 |
SP |
2009-01-30 10:00 |
Nara |
NAIST |
Acoustic Compensation Algorithms for Body Transmitted Speech Conversion Daisuke Miyamoto, Keigo Nakamura, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano (Nara Inst. of Scie and Tech.) SP2008-132 |
Statistical voice conversion is very effective for enhancing body transmitted speech recorded with Non-Audible Murmur (N... [more] |
SP2008-132 pp.37-42 |
SP |
2009-01-30 10:25 |
Nara |
NAIST |
Voice Synthesis Circuit Employing a Pulse Density based on Articulatory Model Hiroshi Kotaki, Jun Nonaka, Hakaru Tamukoh, Masatoshi Sekine (Tokyo Univ. of Agri & Tech) SP2008-133 |
Human various voices are made by a shape of a phonatory organ that changes its complexity with the muscles.In this paper... [more] |
SP2008-133 pp.43-48 |
SP |
2009-01-30 10:50 |
Nara |
NAIST |
Speaker-direction Detection based on Emphasizing Particular Parts of Cross-correlation Function under Robot's Mechanical Noises Tsukasa Nunami, Takeshi Kawabata (Kwansei Gakuin Univ.) SP2008-134 |
A phoneme-cue based speaker-direction detection mechanism for toy/home robots is improved using the composite similarity... [more] |
SP2008-134 pp.49-53 |
SP |
2009-01-30 11:25 |
Nara |
NAIST |
Clustering to make a set of templates for voicing rate and pitch determination Yosuke Kataguchi, Hideo Miyabayashi (Toyama National College of Maritime Tech.) SP2008-135 |
In our past voiced/unvoiced detection, we have classified speech sections with two values. In this study, we introduce v... [more] |
SP2008-135 pp.55-60 |
SP |
2009-01-30 11:50 |
Nara |
NAIST |
Syllable Clustering using Only Linguistic Information for "Word Synthesis by Concatenating Syllabic Components" Kazuhisa Uemura, Jin'ichi Murakami, Satoru Ikehara (Tottori Univ.) SP2008-136 |
``Word synthesis by concatenating syllabic components'' is proposed as a
speech synthesis method. As a problem of this... [more] |
SP2008-136 pp.61-66 |
SP |
2009-01-30 12:15 |
Nara |
NAIST |
Speech synthesis based on the plural unit selection and fusion method using FWF model. Ryo Morinaka, Masatsune Tamura, Masahiro Morita, Takehiko Kagoshima (Toshiba Co.) SP2008-137 |
In the conventional plural unit selection and fusion method, there are problems about degradation in synthesized sound f... [more] |
SP2008-137 pp.67-72 |
SP |
2009-01-30 13:40 |
Nara |
NAIST |
[Invited Talk]
Statistical Voice Quality Transformation and Control Methods for Arbitrary Speakers Tomoki Toda (Nara Inst. of Scie and Tech.) SP2008-138 |
Voice conversion (VC) is a technique to modify nonlinguistic information such as voice characteristics while keeping lin... [more] |
SP2008-138 pp.73-78 |
SP |
2009-01-30 14:40 |
Nara |
NAIST |
Mixture of Probabilistic Linear Regression for Voice Conversion Yu Qiao, Daisuke Saito, Nobuaki Minematsu (Univ. of Tokyo) SP2008-139 |
This paper introduces a model of Mixture of Probabilistic Linear Regressions (MPLR) to learn a mapping function between ... [more] |
SP2008-139 pp.79-84 |
SP |
2009-01-30 15:05 |
Nara |
NAIST |
Many-to-many eigenvoice conversion algorithms with a reference speaker Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano (Nara Inst. of Scie and Tech.) SP2008-140 |
In this paper, we propose many-to-many voice conversion (VC) technique to convert an arbitrary source speaker's voice in... [more] |
SP2008-140 pp.85-90 |
SP |
2009-01-30 15:30 |
Nara |
NAIST |
Low-delay voice conversion algorithm based on maximum likelihood estimation of spectral parameter trajectory Takashi Muramatsu, Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano (Nara Inst. of Scie and Tech.) SP2008-141 |
In this paper, we aim to achieve high-quality and real-time VC considering spectral conversion method and post-processin... [more] |
SP2008-141 pp.91-96 |