Information and Systems-Natural Language Understanding and Models of Communication(Date:2003/12/11)

Presentation
表紙

,  

[Date]2003/12/11
[Paper #]
目次

,  

[Date]2003/12/11
[Paper #]
Deterministic Annealing EM algorithm for speaker and speech recognition

Y. ITAYA,  H. ZEN,  Y. NANKAKU,  C. MIYAJIMA,  K. TOKUDA,  T. KITAMURA,  

[Date]2003/12/11
[Paper #]NLC2003-50
Extraction of high confidence portions of recognition results and unsupervised adaptation using them on lecture speech

Tomohiro WATANABE,  Hiromitsu NISHIZAKI,  Takehito UTSURO,  Seiichi NAKAGAWA,  

[Date]2003/12/11
[Paper #]NLC2003-51
Real-time Frequency Characteristic Normalization for ETSI DSR Front-end

Satoru TSUGE,  Shingo KUROIWA,  Kazuma HARA,  Kenji KITA,  

[Date]2003/12/11
[Paper #]NLC2003-52
Noise-robust speech recognition using band-dependent weighted likelihood

Yoshitaka NISHIMURA,  Takahiro SHINOZAKI,  Koji IWANO,  Sadaoki FURUI,  

[Date]2003/12/11
[Paper #]NLC2003-53
Additive and Channel Noise Suppression Method Based on GMM and EM Algorithm

Masakiyo FUJIMOTO,  Yasuo ARIKI,  

[Date]2003/12/11
[Paper #]NLC2003-54
Research on the factor that influence recognition accuracy of large scale In-Car Spoken Dialogue Database

Hiroshi FUJIMURA,  Katsunobu ITOU,  Kazuya TAKEDA,  Fumitada ITAKURA,  

[Date]2003/12/11
[Paper #]NLC2003-55
Performance Prediction of Noisy Speech Recognition Using PESQ and Artificial Voice

Takeshi YAMADA,  Nobuhiko KITAWAKI,  

[Date]2003/12/11
[Paper #]NLC2003-56
The Succesive State Splitting Algorithm based on the Variational Bayesian Approach

Takatoshi JITSUHIRO,  Satoshi NAKAMURA,  

[Date]2003/12/11
[Paper #]NLC2003-57
Rapid EM Training Technique Based on Model-Integration

Shinichi YOSHIZAWA,  Kiyohiro SHIKANO,  

[Date]2003/12/11
[Paper #]NLC2003-58
A Trajectory Model Derived from HMM with Explicit Relationship between Static and Dynamic Features

Heiga ZEN,  Keiichi TOKUDA,  Tadashi KITAMURA,  

[Date]2003/12/11
[Paper #]NLC2003-59
Performance Improvement of the Language Model Using Adaptive Interpolation of Multiple Back-off N-gram Models

Rikiya TAKAHASHI,  Nobuaki MINEMATSU,  Keikichi HIROSE,  

[Date]2003/12/11
[Paper #]NLC2003-60
Language Model Adaptation based on PLSA on Topics and Speakers

Yuya AKITA,  Tatsuya KAWAHARA,  

[Date]2003/12/11
[Paper #]NLC2003-61
Automatic Extraction of Key Sentences from CSJ Lectures using Statistics of Presumed Discourse Markers

Hiroaki NANJO,  Tasuku KITADE,  Tatsuya KAWAHARA,  

[Date]2003/12/11
[Paper #]NLC2003-62
Extraction of Important Sentences for Speech Summarization Using Prosodic Information and Linguistic Information by Continuous Speech Recognition

Akira INOUE,  Takayoshi MIKAMI,  Yoichi YAMASHITA,  

[Date]2003/12/11
[Paper #]NLC2003-63
Speaker Adaptation of Bilingual Phone Models using Bilingual Speakers' Speech

Hirokazu OGASAWARA,  Yuichi OHKAWA,  Motoyuki SUZUKI,  Akinori ITO,  Shozo MAKINO,  

[Date]2003/12/11
[Paper #]NLC2003-64
Parameter Sharing of Mixtures of Factor Analyzers for Speaker Identification

H. YAMAMOTO,  Y. NANKAKU,  C. MIYAJIMA,  K. TOKUDA,  T. KITAMURA,  

[Date]2003/12/11
[Paper #]NLC2003-65
Adult and Child Discrimination for Flexible Spoken Guidance System

Ryuichi NISIMURA,  Keisuke NAKAMURA,  Akinobu LEE,  Hiroshi SARUWATARI,  Kiyoshiko SHIKANO,  

[Date]2003/12/11
[Paper #]NLC2003-66
Evaluation of ETSI STQ Aurora WI008 Advanced DSR Frontend Using AURORA-2J

Takeshi YAMADA,  Kazuya TAKEDA,  Norihide KITAOKA,  Masakiyo FUJIMOTO,  Shingo KUROIWA,  Kazumasa YAMAMOTO,  Takanobu NISHIURA,  Akira SASOU,  Mitsunori MIZUMACHI,  Toshiki ENDO,  Satoshi NAKAMURA,  

[Date]2003/12/11
[Paper #]NLC2003-67
123>> 1-20hit(45hit)