


default search action
INTERSPEECH 2004: Lisbon, Portugal
- 8th International Conference on Spoken Language Processing, INTERSPEECH-ICSLP 2004, Jeju Island, Korea, October 4-8, 2004. ISCA 2004
Plenary Talks
- Chin-Hui Lee:
From decoding-driven to detection-based paradigms for automatic speech recognition. - Hyun-Bok Lee:
In search of a universal phonetic alphabet - theory and application of an organic visible speech-. - Jacqueline Vaissière:
From X-ray or MRU data to sounds through articulatory synthesis: towards an integrated view of the speech communication process.
Speech Recognition - Adaptation
- Sreeram Balakrishnan, Karthik Visweswariah, Vaibhava Goel:
Stochastic gradient adaptation of front-end parameters. 1-4 - Antoine Raux, Rita Singh:
Maximum - likelihod adaptation of semi-continuous HMMs by latent variable decomposition of state distributions. 5-8 - Chao Huang, Tao Chen, Eric Chang:
Transformation and combination of hiden Markov models for speaker selection training. 9-12 - Brian Kan-Wing Mak, Roger Wend-Huu Hsiao:
Improving eigenspace-based MLLR adaptation by kernel PCA. 13-16 - Nikos Chatzichrisafis, Vassilios Digalakis, Vassilios Diakoloukas, Costas Harizakis:
Rapid acoustic model development using Gaussian mixture clustering and language adaptation. 17-20 - Karthik Visweswariah, Ramesh A. Gopinath:
Adaptation of front end parameters in a speech recognizer. 21-24 - Diego Giuliani, Matteo Gerosa, Fabio Brugnara:
Speaker normalization through constrained MLLR based transforms. 2893-2896 - Xiangyu Mu, Shuwu Zhang, Bo Xu:
Multi-layer structure MLLR adaptation algorithm with subspace regression classes and tying. 2897-2900 - Georg Stemmer, Stefan Steidl, Christian Hacker, Elmar Nöth:
Adaptation in the pronunciation space for non-native speech recognition. 2901-2904 - Xuechuan Wang, Douglas D. O'Shaughnessy:
Robust ASR model adaptation by feature-based statistical data mapping. 2905-2908 - Zhaobing Han, Shuwu Zhang, Bo Xu:
A novel target-driven generalized JMAP adaptation algorithm. 2909-2912 - Brian Mak, Simon Ka-Lung Ho, James T. Kwok:
Speedup of kernel eigenvoice speaker adaptation by embedded kernel PCA. 2913-2916 - Hyung Bae Jeon, Dong Kook Kim:
Maximum a posteriori eigenvoice speaker adaptation for Korean connected digit recognition. 2917-2920 - Wei Wang, Stephen A. Zahorian:
Vocal tract normalization based on spectral warping. 2921-2924 - Koji Tanaka, Fuji Ren, Shingo Kuroiwa, Satoru Tsuge:
Acoustic model adaptation for coded speech using synthetic speech. 2925-2928 - Motoyuki Suzuki, Hirokazu Ogasawara, Akinori Ito, Yuichi Ohkawa, Shozo Makino:
Speaker adaptation method for CALL system using bilingual speakers' utterances. 2929-2932 - Shinji Watanabe:
Acoustic model adaptation based on coarse/fine training of transfer vectors and its application to a speaker adaptation task. 2933-2936 - Wei-Ho Tsai, Shih-Sian Cheng, Hsin-Min Wang:
Speaker clustering of speech utterances using a voice characteristic reference space. 2937-2940 - Young Kuk Kim, Hwa Jeon Song, Hyung Soon Kim:
Performance improvement of connected digit recognition using unsupervised fast speaker adaptation. 2941-2944 - Hyung Soon Kim, Hwa Jeon Song:
Simultaneous estimation of weights of eigenvoices and bias compensation vector for rapid speaker adaptation. 2945-2948 - Matthias Wölfel:
Speaker dependent model order selection of spectral envelopes. 2949-2952 - Enrico Bocchieri, Michael Riley, Murat Saraclar:
Methods for task adaptation of acoustic models with limited transcribed in-domain data. 2953-2956 - Atsushi Fujii, Tetsuya Ishikawa, Katsunobu Itou, Tomoyosi Akiba:
Unsupervised topic adaptation for lecture speech retrieval. 2957-2960 - Haibin Liu, Zhenyang Wu:
Mean and covariance adaptation based on minimum classification error linear regression for continuous density HMMs. 2961-2964 - Goshu Nagino, Makoto Shozakai:
Design of ready-made acoustic model library by two-dimensional visualization of acoustic space. 2965-2968
Spoken Language Identification, Translation and Retrieval I
- Jean-Luc Gauvain, Abdelkhalek Messaoudi, Holger Schwenk:
Language recognition using phone latices. 25-28 - Mark A. Huckvale:
ACCDIST: a metric for comparing speakers' accents. 29-32 - Michael Levit, Allen L. Gorin, Patrick Haffner, Hiyan Alshawi, Elmar Nöth:
Aspects of named entity processing. 33-36 - Josep Maria Crego, José B. Mariño, Adrià de Gispert:
Finite-state-based and phrase-based statistical machine translation. 37-40 - Tanja Schultz, Szu-Chen Stan Jou, Stephan Vogel, Shirin Saleem:
Using word latice information for a tighter coupling in speech translation systems. 41-44 - Teruhisa Misu, Tatsuya Kawahara, Kazunori Komatani:
Confirmation strategy for document retrieval systems with spoken dialog interface. 45-48 - Shi-wook Lee, Kazuyo Tanaka, Yoshiaki Itoh:
Multilayer subword units for open-vocabulary spoken document retrieval. 1553-1556 - Yoshiaki Itoh, Kazuyo Tanaka, Shi-wook Lee:
An efficient partial matching algorithm toward speech retrieval by speech. 1557-1560 - Celestin Sedogbo, Sébastien Herry, Bruno Gas, Jean-Luc Zarader:
Language detection by neural discrimination. 1561-1564 - Ricardo de Córdoba, Javier Ferreiros, Valentín Sama, Javier Macías Guarasa, Luis Fernando D'Haro, Fernando Fernández Martínez:
Language identification techniques based on full recognition in an air traffic control task. 1565-1568 - John H. L. Hansen, Umit H. Yapanel, Rongqing Huang, Ayako Ikeno:
Dialect analysis and modeling for automatic classification. 1569-1572 - Emmanuel Ferragne, François Pellegrino:
Rhythm in read british English: interdialect variability. 1573-1576 - Pascale Fung, Yi Liu, Yongsheng Yang, Yihai Shen, Dekai Wu:
A grammar-based Chinese to English speech translation system for portable devices. 1577-1580 - Gökhan Tür:
Cost-sensitive call classification. 1581-1584 - Mikko Kurimo, Ville T. Turunen, Inger Ekman:
An evaluation of a spoken document retrieval baseline system in finish. 1585-1588 - Hui Jiang, Pengfei Liu, Imed Zitouni:
Discriminative training of naive Bayes classifiers for natural language call routing. 1589-1592 - Nicolas Moreau, Hyoung-Gook Kim, Thomas Sikora:
Phonetic confusion based document expansion for spoken document retrieval. 1593-1596 - Euisok Chung, Soojong Lim, Yi-Gyu Hwang, Myung-Gil Jang:
Hybrid named entity recognition for question-answering system. 1597-1600 - Jitendra Ajmera, Iain McCowan, Hervé Bourlard:
An online audio indexing system. 1601-1604 - Eric Sanders, Febe de Wet:
Histogram normalisation and the recognition of names and ontology words in the MUMIS project. 1605-1608 - Rui Amaral, Isabel Trancoso:
Improving the topic indexation and segmentation modules of a media watch system. 1609-1612 - Melissa Barkat-Defradas, Rym Hamdi, Emmanuel Ferragne, François Pellegrino:
Speech timing and rhythmic structure in arabic dialects: a comparison of two approaches. 1613-1616 - Hsin-Min Wang, Shih-Sian Cheng:
METRIC-SEQDAC: a hybrid approach for audio segmentation. 1617-1620 - Jen-Wei Kuo, Yao-Min Huang, Berlin Chen, Hsin-Min Wang:
Statistical Chinese spoken document retrieval using latent topical information. 1621-1624 - Masahiko Matsushita, Hiromitsu Nishizaki, Seiichi Nakagawa, Takehito Utsuro:
Keyword recognition and extraction by multiple-LVCSRs with 60, 000 words in speech-driven WEB retrieval task. 1625-1628 - Ruiqiang Zhang, Gen-ichiro Kikui, Hirofumi Yamamoto, Frank K. Soong, Taro Watanabe, Eiichiro Sumita, Wai Kit Lo:
Improved spoken language translation using n-best speech recognition hypotheses. 1629-1632 - Kakeung Wong, Man-Hung Siu:
Automatic language identification using discrete hidden Markov model. 1633-1636 - Bowen Zhou, Daniel Déchelotte, Yuqing Gao:
Two-way speech-to-speech translation on handheld devices. 1637-1640 - Hervé Blanchon:
HLT modules scalability within the NESPOLE! project. 1641-1644
Linguistics, Phonology, and Phonetics
- Midam Kim:
Correlation between VOT and F0 in the perception of Korean stops and affricates. 49-52 - Aude Noiray, Lucie Ménard, Marie-Agnès Cathiard, Christian Abry, Christophe Savariaux:
The development of anticipatory labial coarticulation in French: a pionering study. 53-56 - Melvyn John Hunt:
Speech recognition, sylabification and statistical phonetics. 57-60 - Jilei Tian:
Data-driven approaches for automatic detection of syllable boundaries. 61-64 - Anne Cutler, Dennis Norris, Núria Sebastián-Gallés:
Phonemic repertoire and similarity within the vocabulary. 65-68 - Sameer Maskey, Alan W. Black, Laura Tomokiya:
Boostrapping phonetic lexicons for new languages. 69-72 - Mirjam Broersma, K. Marieke Kolkman:
Lexical representation of non-native phonemes. 1241-1244 - Jong-Pyo Lee, Tae-Yeoub Jang:
A comparative study on the production of inter-stress intervals of English speech by English native speakers and Korean speakers. 1245-1248 - Emi Zuiki Murano, Mihoko Teshigawara:
Articulatory correlates of voice qualities of god guys and bad guys in Japanese anime: an MRI study. 1249-1252 - Sorin Dusan:
Effects of phonetic contexts on the duration of phonetic segments in fluent read speech. 1253-1256 - Qiang Fang:
A study on nasal coda los in continuous speech. 1257-1260 - Hua-Li Jian:
An improved pair-wise variability index for comparing the timing characteristics of speech. 1261-1264 - Hua-Li Jian:
An acoustic study of speech rhythm in taiwan English. 1265-1268 - Sung-A. Kim:
Language specific phonetic rules: evidence from domain-initial strengthening. 1269-1272 - Hansang Park:
Spectral characteristics of the release bursts in Korean alveolar stops. 1273-1276 - Rob van Son, Olga Bolotova, Louis C. W. Pols, Mietta Lennes:
Frequency effects on vowel reduction in three typologically different languages (dutch, finish, Russian). 1277-1280 - Julia Abresch, Stefan Breuer:
Assessment of non-native phones in anglicisms by German listeners. 1281-1284 - Sunhee Kim:
Phonology of exceptions for for Korean grapheme-to-phoneme conversion. 1285-1289 - Shigeyoshi Kitazawa, Shinya Kiriyama:
Acoustic and prosodic analysis of Japanese vowel-vowel hiatus with laryngeal effect. 1289-1293 - Kimiko Tsukada:
A cross-linguistic acoustic comparison of unreleased word-final stops: Korean and Thai. 1293-1296 - Taehong Cho, Elizabeth K. Johnson:
Acoustic correlates of phrase-internal lexical boundaries in dutch. 1297-1300 - Taehong Cho, James M. McQueen:
Phonotactics vs. phonetic cues in native and non-native listening: dutch and Korean listeners' perception of dutch and English. 1301-1304 - Svetlana Kaminskaia, François Poiré:
Comparing intonation of two varieties of French using normalized F0 values. 1305-1308 - Mira Oh, Kee-Ho Kim:
Phonetic realization of the suffix-suppressed accentual phrase in Korean. 1309-1312 - H. Timothy Bunnell, James B. Polikoff, Jane McNicholas:
Spectral moment vs. bark cepstral analysis of children's word-initial voiceles stops. 1313-1316 - Nobuaki Minematsu:
Pronunciation assessment based upon the compatibility between a learner's pronunciation structure and the target language's lexical structure. 1317-1320 - Kenji Yoshida:
Spread of high tone in akita Japanese. 1321-1324
Biomedical Applications of Speech Analysis
- Juan Ignacio Godino-Llorente, María Victoria Rodellar Biarge, Pedro Gómez Vilda, Francisco Díaz Pérez, Agustín Álvarez Marquina, Rafael Martínez-Olalla:
Biomechanical parameter fingerprint in the mucosal wave power spectral density. 73-76 - Cheolwoo Jo, Soo-Geon Wang, Byung-Gon Yang, Hyung-Soon Kim, Tao Li:
Classification of pathological voice including severely noisy cases. 77-80 - Qiang Fu, Peter Murphy:
A robust glottal source model estimation technique. 81-84 - Hiroki Mori, Yasunori Kobayashi, Hideki Kasuya, Hajime Hirose, Noriko Kobayashi:
F0 and formant frequency distribution of dysarthric speech - a comparative study. 85-88 - Hideki Kawahara, Yumi Hirachi, Masanori Morise, Hideki Banno:
Procedure "senza vibrato": a key component for morphing singing. 89-92 - Claudia Manfredi, Giorgio Peretti, Laura Magnoni, Fabrizio Dori, Ernesto Iadanza:
Thyroplastic medialisation in unilateral vocal fold paralysis: assessing voice quality recovering. 93-96 - Gernot Kubin, Martin Hagmüller:
Voice enhancement of male speakers with laryngeal neoplasm. 541-544 - Jong Min Choi, Myung-Whun Sung, Kwang Suk Park, Jeong-Hun Hah:
A comparison of the perturbation analysis between PRAAT and computerize speech lab. 545-548
Robust Speech Recognition on AURORA
- Ji Ming, Baochun Hou:
Evaluation of universal compensation on Aurora 2 and 3 and beyond. 97-100 - Hugo Van hamme:
PROSPECT features and their application to missing data techniques for robust speech recognition. 101-104 - Hugo Van hamme, Patrick Wambacq, Veronique Stouten:
Accounting for the uncertainty of speech estimates in the context of model-based feature enhancement. 105-108 - Hans-Günter Hirsch, Harald Finster:
Applying the Aurora feature extraction schemes to a phoneme based recognition task. 109-112 - Zhipeng Zhang, Tomoyuki Ohya, Sadaoki Furui:
Evaluation of tree-structured piecewise linear transformation-based noise adaptation on AURORA2 database. 113-116 - Tor André Myrvoll, Satoshi Nakamura:
Online minimum mean square error filtering of noisy cepstral coefficients using a sequential EM algorithm. 117-120 - Akira Sasou, Kazuyo Tanaka, Satoshi Nakamura, Futoshi Asano:
HMM-based feature compensation method: an evaluation using the AURORA2. 121-124 - Xuechuan Wang, Douglas D. O'Shaughnessy:
Noise adaptation for robust AURORA 2 noisy digit recognition using statistical data mapping. 125-128 - Benjamin J. Shannon, Kuldip K. Paliwal:
MFCC computation from magnitude spectrum of higher lag autocorrelation coefficients for robust speech recognition. 129-132 - Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, Tsuneo Nitta:
A noise-robust feature extraction method based on pitch-synchronous ZCPA for ASR. 133-136 - José C. Segura, Ángel de la Torre, Javier Ramírez, Antonio J. Rubio, M. Carmen Benítez:
Including uncertainty of speech observations in robust speech recognition. 137-140 - Takeshi Yamada, Jiro Okada, Nobuhiko Kitawaki:
Integration of n-best recognition results obtained by multiple noise reduction algorithms. 141-144 - Panji Setiawan, Sorel Stan, Tim Fingscheidt:
Revisiting some model-based and data-driven denoising algorithms in Aurora 2 context. 145-148 - Guo-Hong Ding, Bo Xu:
Exploring high-performance speech recognition in noisy environments using high-order taylor series expansion. 149-152 - Wing-Hei Au, Man-Hung Siu:
A robust training algorithm based on neighborhood information. 153-156 - Siu Wa Lee, Pak-Chung Ching:
In-phase feature induction: an effective compensation technique for robust speech recognition. 157-160 - Jeff Siu-Kei Au-Yeung, Man-Hung Siu:
Improved performance of Aurora 4 using HTK and unsupervised MLLR adaptation. 161-164 - Shang-nien Tsai, Lin-Shan Lee:
A new feature extraction front-end for robust speech recognition using progressive histogram equalization and multi-eigenvector temporal filtering. 165-168
Spoken / Multimodal Dialogue System
- Christian Fügen, Hartwig Holzapfel, Alex Waibel:
Tight coupling of speech recognition and dialog management - dialog-context dependent grammar weighting for speech recognition. 169-172 - Akinobu Lee, Keisuke Nakamura, Ryuichi Nisimura, Hiroshi Saruwatari, Kiyohiro Shikano:
Noise robust real world spoken dialogue system using GMM based rejection of unintended inputs. 173-176 - Hironori Oshikawa, Norihide Kitaoka, Seiichi Nakagawa:
Speech interface for name input based on combination of recognition methods using syllable-based n-gram and word dictionary. 177-180 - Imed Zitouni, Minkyu Lee, Hui Jiang:
Constrained minimization technique for topic identification using discriminative training and support vector machines. 181-184 - Jason D. Williams, Steve J. Young:
Characterizing task-oriented dialog using a simulated ASR chanel. 185-188 - Takashi Konashi, Motoyuki Suzuki, Akinori Ito, Shozo Makino:
A spoken dialog system based on automatic grammar generation and template-based weighting for autonomous mobile robots. 189-192 - Akinori Ito, Takanobu Oba, Takashi Konashi, Motoyuki Suzuki, Shozo Makino:
Noise adaptive spoken dialog system based on selection of multiple dialog strategies. 193-196 - Mikko Hartikainen, Markku Turunen, Jaakko Hakulinen, Esa-Pekka Salonen, J. Adam Funk:
Flexible dialogue management using distributed and dynamic dialogue control. 197-200 - Keith Houck:
Contextual revision in information seeking conversation systems. 201-204 - Ian M. O'Neill, Philip Hanna, Xingkun Liu, Michael F. McTear:
Cross domain dialogue modelling: an object-based approach. 205-208 - Hirohiko Sagawa, Teruko Mitamura, Eric Nyberg:
A comparison of confirmation styles for error handling in a speech dialog system. 209-212 - Fan Yang, Peter A. Heeman:
Using computer simulation to compare two models of mixed-initiative. 213-216 - Fan Yang, Peter A. Heeman, Kristy Hollingshead:
Towards understanding mixed-initiative in task-oriented dialogues. 217-220 - Peter Wolf, Joseph Woelfel, Jan C. van Gemert, Bhiksha Raj, David Wong:
Spokenquery: an alternate approach to chosing items with speech. 221-224 - Shona Douglas, Deepak Agarwal, Tirso Alonso, Robert M. Bell, Mazin G. Rahim, Deborah F. Swayne, Chris Volinsky:
Mining customer care dialogs for "daily news". 225-228 - Jens Edlund, Gabriel Skantze, Rolf Carlson:
Higgins - a spoken dialogue system for investigating error handling techniques. 229-232