@inproceedings{bb387900,
        AUTHOR = "Tang, J. and Sarokin, R. and Ignasheva, E. and Jensen, G. and Chen, L. and Lee, J. and Kulik, A. and Grundmann, M.",
        TITLE = "Scaling On-Device GPU Inference for Large Generative Models",
        BOOKTITLE = EDGE25,
        YEAR = "2025",
        PAGES = "6345-6354",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381962"}

@inproceedings{bb387901,
        AUTHOR = "Wang, J.Y. and Liu, Z. and Wu, X.Y.",
        TITLE = "LOCO-MAD: Long-range Context-enhanced Model Towards Plot-centric Movie
Audio Description",
        BOOKTITLE = ACCV24,
        YEAR = "2024",
        PAGES = "V: 95-112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381963"}

@article{bb387902,
        AUTHOR = "Lin, J. and Ge, M. and Wang, W. and Li, H.Z. and Feng, M.L.",
        TITLE = "Selective HuBERT: Self-Supervised Pre-Training for Target Speaker in
Clean and Mixture Speech",
        JOURNAL = SPLetters,
        VOLUME = "31",
        YEAR = "2024",
        PAGES = "1014-1018",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381964"}

@inproceedings{bb387903,
        AUTHOR = "Feng, Y. and Liu, Z.Y. and Luo, S. and Ling, Y. and Dong, S. and Wang, S.Y. and Ferry, B.",
        TITLE = "Noise-Free Audio Signal Processing in Noisy Environment:
A Hardware and Algorithm Solution",
        BOOKTITLE = VAQuality24,
        YEAR = "2024",
        PAGES = "368-373",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381965"}

@inproceedings{bb387904,
        AUTHOR = "Ng, H.W. and Guan, C.T.",
        TITLE = "Efficient Representation Learning for Inner Speech Domain
Generalization",
        BOOKTITLE = CAIP23,
        YEAR = "2023",
        PAGES = "I:131-141",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381966"}

@inproceedings{bb387905,
        AUTHOR = "Oneata, D. and Cucu, H.",
        TITLE = "Improving Multimodal Speech Recognition by Data Augmentation and
Speech Representations",
        BOOKTITLE = MULA22,
        YEAR = "2022",
        PAGES = "4578-4587",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381967"}

@inproceedings{bb387906,
        AUTHOR = "Tapia, L.S. and Gomez, A. and Esparza, M. and Jatla, V. and Pattichis, M. and Celedon Pattichis, S. and Lopez Leiva, C.",
        TITLE = "Bilingual Speech Recognition by Estimating Speaker Geometry from Video
Data",
        BOOKTITLE = CAIP21,
        YEAR = "2021",
        PAGES = "I:79-89",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381968"}

@inproceedings{bb387907,
        AUTHOR = "Qiao, F.C. and Peng, X.",
        TITLE = "Uncertainty-guided Model Generalization to Unseen Domains",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "6786-6796",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381969"}

@inproceedings{bb387908,
        AUTHOR = "Ngantcha, P. and Amith, M. and Tao, C. and Roberts, K.",
        TITLE = "Patient-Provider Communication Training Models for Interactive Speech
Devices",
        BOOKTITLE = DHM21,
        YEAR = "2021",
        PAGES = "I:250-268",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381970"}

@inproceedings{bb387909,
        AUTHOR = "Wu, Y.C. and Liao, W.H.",
        TITLE = "Toward Text-independent Cross-lingual Speaker Recognition Using
English-Mandarin-Taiwanese Dataset",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "8515-8522",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381971"}

@inproceedings{bb387910,
        AUTHOR = "Chen, Y.B. and Ma, Y. and Ko, T. and Wang, J.P. and Li, Q.",
        TITLE = "MetaMix: Improved Meta-Learning with Interpolation-based Consistency
Regularization",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "407-414",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381972"}

@inproceedings{bb387911,
        AUTHOR = "Zhou, L.X. and Zhang, J.",
        TITLE = "From Bottom to Top: A Coordinated Feature Representation Method for
Speech Recognition",
        BOOKTITLE = MMDLCA20,
        YEAR = "2020",
        PAGES = "396-403",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381973"}

@inproceedings{bb387912,
        AUTHOR = "Zhao, J. and Parry, C.J. and dos Anjos, R. and Anslow, C. and Rhee, T.",
        TITLE = "Voice Interaction for Augmented Reality Navigation Interfaces with
Natural Language Understanding",
        BOOKTITLE = IVCNZ20,
        YEAR = "2020",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381974"}

@inproceedings{bb387913,
        AUTHOR = "ABAKARIM, F. and ABENAOU, A.",
        TITLE = "Amazigh isolated word speech recognition system using the Adaptive
Orthogonal Transform Method.",
        BOOKTITLE = ISCV20,
        YEAR = "2020",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381975"}

@inproceedings{bb387914,
        AUTHOR = "Perez, A.F. and Sanguineti, V. and Morerio, P. and Murino, V.",
        TITLE = "Audio-Visual Model Distillation Using Acoustic Images",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "2843-2852",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381976"}

@inproceedings{bb387915,
        AUTHOR = "Tapu, R. and Mocanu, B. and Zaharia, T.",
        TITLE = "Dynamic Subtitles: A Multimodal Video Accessibility Enhancement
Dedicated to Deaf and Hearing Impaired Users",
        BOOKTITLE = ACVR19,
        YEAR = "2019",
        PAGES = "2558-2566",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381977"}

@inproceedings{bb387916,
        AUTHOR = "Roberto, A. and Saggese, A. and Vento, M.",
        TITLE = "A Challenging Voice Dataset for Robotic Applications in Noisy
Environments",
        BOOKTITLE = CAIP19,
        YEAR = "2019",
        PAGES = "II:354-364",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381978"}

@inproceedings{bb387917,
        AUTHOR = "Gauvain, J. and Lamel, L. and Le, V.B. and Despres, J. and Gauvain, J.L. and Messaoudi, A. and Vieru, B. and Ben Kheder, W.",
        TITLE = "Challenges in Audio Processing of Terrorist-Related Data",
        BOOKTITLE = "MMMod19",
        YEAR = "2019",
        PAGES = "II:80-92",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381979"}

@inproceedings{bb387918,
        AUTHOR = "Jorrin, J. and Buera, L.",
        TITLE = "DANTE Speaker Recognition Module. An Efficient and Robust Automatic
Speaker Searching Solution for Terrorism-Related Scenarios",
        BOOKTITLE = "MMMod19",
        YEAR = "2019",
        PAGES = "I:704-715",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381980"}

@inproceedings{bb387919,
        AUTHOR = "Galanopoulos, D. and Mezaris, V.",
        TITLE = "Temporal Lecture Video Fragmentation Using Word Embeddings",
        BOOKTITLE = "MMMod19",
        YEAR = "2019",
        PAGES = "II:254-265",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381981"}

@inproceedings{bb387920,
        AUTHOR = "Mukherjee, H. and Obaidullah, S.M. and Phadikar, S. and Roy, K.",
        TITLE = "A Dravidian Language Identification System",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "2654-2657",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381982"}

@inproceedings{bb387921,
        AUTHOR = "Galiotou, E. and Karanikolas, N. and Ralli, A.",
        TITLE = "Preservation and Management of Greek Dialectal Data",
        BOOKTITLE = EuroMed18,
        YEAR = "2018",
        PAGES = "I:752-761",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381983"}

@inproceedings{bb387922,
        AUTHOR = "Li, R. and Yu, J.",
        TITLE = "Multimodal 3D visible articulation system for syllable based Mandarin
Chinese training",
        BOOKTITLE = VCIP17,
        YEAR = "2017",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381984"}

@inproceedings{bb387923,
        AUTHOR = "Le, N. and Odobez, J.M.",
        TITLE = "Improving Speaker Turn Embedding by Crossmodal Transfer Learning from
Face Embedding",
        BOOKTITLE = CVAVM17,
        YEAR = "2017",
        PAGES = "428-437",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381985"}

@inproceedings{bb387924,
        AUTHOR = "Arandjelovic, R. and Zisserman, A.",
        TITLE = "Look, Listen and Learn",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "609-617",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381986"}

@inproceedings{bb387925,
        AUTHOR = "Muniandy, T. and Alvar, T.A. and Boon, C.J.",
        TITLE = "Mandarin Language Learning System for Nasal Voice User",
        BOOKTITLE = IVIC17,
        YEAR = "2017",
        PAGES = "376-388",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381987"}

@inproceedings{bb387926,
        AUTHOR = "Madhavi, M.C. and Patil, H.A. and Bhendawade, N.",
        TITLE = "Spoken Keyword Retrieval Using Source and System Features",
        BOOKTITLE = PReMI17,
        YEAR = "2017",
        PAGES = "333-341",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381988"}

@inproceedings{bb387927,
        AUTHOR = "Kacprzak, S.",
        TITLE = "Spoken language clustering in the i-vectors space",
        BOOKTITLE = WSSIP17,
        YEAR = "2017",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381989"}

@inproceedings{bb387928,
        AUTHOR = "Pironkov, G. and Dupont, S. and Dutoit, T.",
        TITLE = "Speaker-aware Multi-Task Learning for automatic speech recognition",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2900-2905",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381990"}

@inproceedings{bb387929,
        AUTHOR = "Zhao, Y. and Zhao, R. and Wang, X.Y. and Ji, Q.",
        TITLE = "Multilingual articulatory features augmentation learning",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2895-2899",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381991"}

@inproceedings{bb387930,
        AUTHOR = "Ogawa, T. and Mallidi, S.H. and Dupoux, E. and Cohen, J. and Feldman, N.H. and Hermansky, H.",
        TITLE = "A new efficient measure for accuracy prediction and its application
to multistream-based unsupervised adaptation",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2222-2227",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381992"}

@inproceedings{bb387931,
        AUTHOR = "Mzah, Y. and Ahfir, M. and Jaidane, M.",
        TITLE = "Late pre-dereverberation for speech intelligibility enhancement in
public address systems",
        BOOKTITLE = ISIVC16,
        YEAR = "2016",
        PAGES = "291-296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381993"}

@inproceedings{bb387932,
        AUTHOR = "Montalvo, A. and Calvo, J.R.",
        TITLE = "Discriminative Capacity and Phonetic Information of Bottleneck Features
in Speech",
        BOOKTITLE = CIARP16,
        YEAR = "2016",
        PAGES = "134-141",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381994"}

@inproceedings{bb387933,
        AUTHOR = "Ondas, S. and Juhar, J.",
        TITLE = "Towards human-machine dialog in Slovak",
        BOOKTITLE = WSSIP16,
        YEAR = "2016",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381995"}

@inproceedings{bb387934,
        AUTHOR = "Calvo, M. and Hurtado, L.F. and Garcia, F. and Sanchis, E.",
        TITLE = "Combining Several ASR Outputs in a Graph-Based SLU System",
        BOOKTITLE = CIARP15,
        YEAR = "2015",
        PAGES = "551-558",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381996"}

@inproceedings{bb387935,
        AUTHOR = "Rohrbach, A. and Rohrbach, M. and Schiele, B.",
        TITLE = "The Long-Short Story of Movie Description",
        BOOKTITLE = GCPR15,
        YEAR = "2015",
        PAGES = "209-221",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381997"}

@inproceedings{bb387936,
        AUTHOR = "Rohrbach, A. and Rohrbach, M. and Tandon, N. and Schiele, B.",
        TITLE = "A dataset for Movie Description",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "3202-3212",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381998"}

@inproceedings{bb387937,
        AUTHOR = "Zhao, H.Q. and Qin, Z.C. and Wang, Y. and Wang, Y.X.",
        TITLE = "A Bag-of-phonemes Model for Homeplace Classification of Mandarin
Speakers",
        BOOKTITLE = IbPRIA15,
        YEAR = "2015",
        PAGES = "683-690",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT381999"}

@inproceedings{bb387938,
        AUTHOR = "Yakubu, M.A. and Maddage, N.C. and Atrey, P.K.",
        TITLE = "Audio Secret Management Scheme Using Shamir's Secret Sharing",
        BOOKTITLE = MMMod15,
        YEAR = "2015",
        PAGES = "I: 396-407",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382000"}

@inproceedings{bb387939,
        AUTHOR = "Bello, C. and Ribas, D. and Calvo, J.R. and Ferrer, C.A.",
        TITLE = "From Speech Quality Measures to Speaker Recognition Performance",
        BOOKTITLE = CIARP14,
        YEAR = "2014",
        PAGES = "199-206",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382001"}

@inproceedings{bb387940,
        AUTHOR = "Oropeza Rodriguez, J.L. and Suarez Guerra, S. and Jimenez Hernandez, M.",
        TITLE = "The Place Theory as an Alternative Solution in Automatic Speech
Recognition Tasks",
        BOOKTITLE = CIARP14,
        YEAR = "2014",
        PAGES = "167-174",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382002"}

@article{bb387941,
        AUTHOR = "Diez, M. and Varona, A. and Penagarikano, M. and Rodriguez Fuentes, L.J. and Bordel, G.",
        TITLE = "On the Projection of PLLRs for Unbounded Feature Distributions in
Spoken Language Recognition",
        JOURNAL = SPLetters,
        VOLUME = "21",
        YEAR = "2014",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1073-1077",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382003"}

@inproceedings{bb387942,
        AUTHOR = "Diez, M. and Varona, A. and Penagarikano, M. and Rodriguez Fuentes, L.J. and Bordel, G.",
        TITLE = "Optimizing PLLR Features for Spoken Language Recognition",
        BOOKTITLE = ICPR14,
        YEAR = "2014",
        PAGES = "779-784",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382004"}

@inproceedings{bb387943,
        AUTHOR = "Missaoui, I. and Lachiri, Z.",
        TITLE = "Gabor Filterbank Features for Robust Speech Recognition",
        BOOKTITLE = ICISP14,
        YEAR = "2014",
        PAGES = "665-671",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382005"}

@inproceedings{bb387944,
        AUTHOR = "Carletti, V. and Foggia, P. and Percannella, G. and Saggese, A. and Strisciuglio, N. and Vento, M.",
        TITLE = "Audio surveillance using a bag of aural words classifier",
        BOOKTITLE = AVSS13,
        YEAR = "2013",
        PAGES = "81-86",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382006"}

@inproceedings{bb387945,
        AUTHOR = "Hurtado, L.F. and Calvo, M. and Gomez, J.A. and Garcia, F. and Sanchis, E.",
        TITLE = "A Phonetic-Based Approach to Query-by-Example Spoken Term Detection",
        BOOKTITLE = CIARP13,
        YEAR = "2013",
        PAGES = "I:504-511",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382007"}

@inproceedings{bb387946,
        AUTHOR = "Chaloupka, J. and Nouza, J. and Kucharova, M.",
        TITLE = "Using Various Types of Multimedia Resources to Train System for
Automatic Transcription of Czech Historical Oral Archives",
        BOOKTITLE = MM4CH13,
        YEAR = "2013",
        PAGES = "228-237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382008"}

@inproceedings{bb387947,
        AUTHOR = "Nouza, J. and Cerva, P. and Silovsky, J.",
        TITLE = "Dealing with Bilingualism in Automatic Transcription of Historical
Archive of Czech Radio",
        BOOKTITLE = MM4CH13,
        YEAR = "2013",
        PAGES = "238-246",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382009"}

@inproceedings{bb387948,
        AUTHOR = "Chan, K.Y. and Nordholm, S.E. and Yiu, C.K.F.",
        TITLE = "Multichannel filters for speech recognition using a particle swarm
optimization",
        BOOKTITLE = ICARCV12,
        YEAR = "2012",
        PAGES = "937-942",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382010"}

@inproceedings{bb387949,
        AUTHOR = "Zhao, Y. and Xu, X.N. and Yang, G.S.",
        TITLE = "Unsupervised Tibetan speech features Learning based on Dynamic Bayesian
Networks",
        BOOKTITLE = ICPR12,
        YEAR = "2012",
        PAGES = "2319-2322",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382011"}

@inproceedings{bb387950,
        AUTHOR = "Nour Eddine, L. and Abdelkader, A.",
        TITLE = "Reduced Universal Background Model for Speech Recognition and
Identification System",
        BOOKTITLE = MCPR12,
        YEAR = "2012",
        PAGES = "303-312",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382012"}

@inproceedings{bb387951,
        AUTHOR = "Amrous, A.I. and Debyeche, M.",
        TITLE = "Robust Arabic Multi-stream Speech Recognition System in Noisy
Environment",
        BOOKTITLE = ICISP12,
        YEAR = "2012",
        PAGES = "571-578",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382013"}

@inproceedings{bb387952,
        AUTHOR = "Touazi, A. and Debyeche, M.",
        TITLE = "New Encoding Algorithm for Distributed Speech Recognition Based on DTFS
Transform",
        BOOKTITLE = ICISP12,
        YEAR = "2012",
        PAGES = "547-554",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382014"}

@inproceedings{bb387953,
        AUTHOR = "Ghigi, F. and Tamarit, V. and Martinez Hinarejos, C.D. and Benedi, J.M.",
        TITLE = "Active Learning for Dialogue Act Labelling",
        BOOKTITLE = IbPRIA11,
        YEAR = "2011",
        PAGES = "652-659",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382015"}

@inproceedings{bb387954,
        AUTHOR = "Meng, L. and Xiang, J. and Zhao, D. and Zhao, H.",
        TITLE = "A New Application of MEG and DTI on Word Recognition",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "2472-2475",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382016"}

@inproceedings{bb387955,
        AUTHOR = "O'Gorman, L.",
        TITLE = "Latency in Speech Feature Analysis for Telepresence Event Coding",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4464-4467",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382017"}

@inproceedings{bb387956,
        AUTHOR = "Zhang, S.L. and Shi, Q. and Qin, Y.",
        TITLE = "Modeling Syllable-Based Pronunciation Variation for Accented Mandarin
Speech Recognition",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "1606-1609",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382018"}

@inproceedings{bb387957,
        AUTHOR = "Zhang, S.L. and Zhang, S.W. and Xu, B.",
        TITLE = "A Two-level Method for Unsupervised Speaker-based Audio Segmentation",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "IV: 298-301",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382019"}

@inproceedings{bb387958,
        AUTHOR = "Krajewski, J. and Batliner, A. and Kessel, S.",
        TITLE = "Comparing Multiple Classifiers for Speech-Based Detection of
Self-Confidence: A Pilot Study",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "3716-3719",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382020"}

@inproceedings{bb387959,
        AUTHOR = "Nolazco Flores, J.A. and Aceves L., R.A. and Garcia Perera, L.P.",
        TITLE = "Speech Magnitude-Spectrum Information-Entropy (MSIE) for Automatic
Speech Recognition in Noisy Environments",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4364-4367",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382021"}

@inproceedings{bb387960,
        AUTHOR = "Kelly, F. and Harte, N.",
        TITLE = "Auditory Features Revisited for Robust Speech Recognition",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4456-4459",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382022"}

@inproceedings{bb387961,
        AUTHOR = "Xie, Z.Q. and Miao, Z.J.",
        TITLE = "Tone Recognition of Isolated Mandarin Syllables",
        BOOKTITLE = ICISP10,
        YEAR = "2010",
        PAGES = "412-418",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382023"}

@inproceedings{bb387962,
        AUTHOR = "Alotaibi, Y.A. and Alghamdi, M. and Alotaiby, F.",
        TITLE = "Speech Recognition System of Arabic Alphabet Based on a Telephony
Arabic Corpus",
        BOOKTITLE = ICISP10,
        YEAR = "2010",
        PAGES = "122-129",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382024"}

@inproceedings{bb387963,
        AUTHOR = "Lu, G. and Yu, H.Z. and Li, Y.H. and Zhang, R.S.",
        TITLE = "Study on SAMPA_ST for Lhasa Tibetan and realization of automatic
labelling system",
        BOOKTITLE = IASP10,
        YEAR = "2010",
        PAGES = "133-137",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382025"}

@inproceedings{bb387964,
        AUTHOR = "Chen, X.Y. and Jin, H.M. and Yu, H.Z.",
        TITLE = "Acoustic research on long and short vowels in Tibetan Lhasa dialect",
        BOOKTITLE = IASP10,
        YEAR = "2010",
        PAGES = "561-564",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382026"}

@inproceedings{bb387965,
        AUTHOR = "Sahu, V.P. and Mishra, H.K. and Sekhar, C.C.",
        TITLE = "Variational Bayes Adapted GMM Based Models for Audio Clip
Classification",
        BOOKTITLE = PReMI09,
        YEAR = "2009",
        PAGES = "513-518",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382027"}

@inproceedings{bb387966,
        AUTHOR = "Verteletskaya, E. and Sakhnov, K. and Simak, B.",
        TITLE = "Pitch Detection Algorithms and Voiced/Unvoiced Classification for Noisy
Speech",
        BOOKTITLE = WSSIP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382028"}

@inproceedings{bb387967,
        AUTHOR = "Vlaj, D. and Kos, M. and Grasic, M. and Kacic, Z.",
        TITLE = "Influence of Hangover and Hangbefore Criteria on Automatic Speech
Recognition",
        BOOKTITLE = WSSIP09,
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382029"}

@inproceedings{bb387968,
        AUTHOR = "Hanzl, V. and Pollak, P.",
        TITLE = "Accuracy Analysis of Generalized Pronunciation Variant Selection in ASR
Systems",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "399-408",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382030"}

@inproceedings{bb387969,
        AUTHOR = "Camarena Ibarrola, A. and Chavez, E. and Tellez, E.S.",
        TITLE = "Robust Radio Broadcast Monitoring Using a Multi-Band Spectral Entropy
Signature",
        BOOKTITLE = CIARP09,
        YEAR = "2009",
        PAGES = "587-594",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382031"}

@inproceedings{bb387970,
        AUTHOR = "Mantilla Caeiros, A. and Miyatake, M.N. and Perez Meana, H.",
        TITLE = "Isolate Speech Recognition Based on Time-Frequency Analysis Methods",
        BOOKTITLE = CIARP09,
        YEAR = "2009",
        PAGES = "297-304",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382032"}

@inproceedings{bb387971,
        AUTHOR = "Veronkova, J. and Palkova, Z.",
        TITLE = "Perception of Czech in Noise: Stability of Vowels",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "149-161",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382033"}

@inproceedings{bb387972,
        AUTHOR = "Skarnitzl, R.",
        TITLE = "Challenges in Segmenting the Czech Lateral Liquid",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "162-172",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382034"}

@inproceedings{bb387973,
        AUTHOR = "Machac, P.",
        TITLE = "Implications of Acoustic Variation for the Segmentation of the Czech
Trill r",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "173-181",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382035"}

@inproceedings{bb387974,
        AUTHOR = "Jorschick, A.B.",
        TITLE = "Voicing in Labial Plosives in Czech",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "182-189",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382036"}

@inproceedings{bb387975,
        AUTHOR = "Volin, J.",
        TITLE = "Normalization of the Vocalic Space",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "190-200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382037"}

@inproceedings{bb387976,
        AUTHOR = "Rajnoha, J. and Pollak, P.",
        TITLE = "Czech Spontaneous Speech Collection and Annotation:
The Database of Technical Lectures",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "377-385",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382038"}

@inproceedings{bb387977,
        AUTHOR = "Janda, J.",
        TITLE = "Quantitative Analysis of the Relative Local Speech Rate",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "368-376",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382039"}

@inproceedings{bb387978,
        AUTHOR = "Zhang, B. and Zhuang, X. and Huang, P. and Feng, C. and Zhao, J.",
        TITLE = "Application of Uni-Directional Microphone Array for Identifying English
Pronunciation Errors",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382040"}

@inproceedings{bb387979,
        AUTHOR = "Kuremoto, T. and Komoto, T. and Kobayashi, K. and Obayashi, M.",
        TITLE = "A Voice Instruction Learning System Using PL-T-SOM",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382041"}

@inproceedings{bb387980,
        AUTHOR = "Espi, M. and Takeuchi, Y.",
        TITLE = "Substitution of Vocal Folds for Voice Generation by Means of Intra-Oral
Pulse Generator",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382042"}

@inproceedings{bb387981,
        AUTHOR = "Orhan, Z. and Gormez, Z.",
        TITLE = "Evaluation of the Concatenative Turkish Text-to-Speech System",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382043"}

@inproceedings{bb387982,
        AUTHOR = "Cai, Y. and Yuan, J.P. and Hou, C.H. and Yang, J. and Wu, B.",
        TITLE = "Harmonic Enhancement with Noise Reduction of Speech Signal by Comb
Filtering",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382044"}

@inproceedings{bb387983,
        AUTHOR = "Li, W.F. and Billard, A. and Bourlard, H.",
        TITLE = "Keyword Detection for Spontaneous Speech",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382045"}

@inproceedings{bb387984,
        AUTHOR = "Zhang, X.Y. and Yao, J.X. and He, Q.A.",
        TITLE = "Research of STRAIGHT Spectrogram and Difference Subspace Algorithm for
Speech Recognition",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382046"}

@inproceedings{bb387985,
        AUTHOR = "Lu, X. and Matsuda, S. and Unoki, M. and Nakamura, S.",
        TITLE = "Temporal Modulation Normalization for Robust Speech Feature Extraction
and Recognition",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382047"}

@inproceedings{bb387986,
        AUTHOR = "Jun, Y.Z. and Lei, W. and Hao, W.",
        TITLE = "A New Parameter of Speech Character Based on the Bloomfield's Model",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382048"}

@inproceedings{bb387987,
        AUTHOR = "Qasemi Zadeh, B. and Shen, J.L. and O'Neill, I. and Miller, P. and Hanna, P. and Stewart, D. and Wang, H.B.",
        TITLE = "A Speech Based Approach to Surveillance Video Retrieval",
        BOOKTITLE = AVSBS09,
        YEAR = "2009",
        PAGES = "336-339",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382049"}

@inproceedings{bb387988,
        AUTHOR = "Cristani, M. and Pesarin, A. and Drioli, C. and Tavano, A. and Perina, A. and Murino, V.",
        TITLE = "Auditory dialog analysis and understanding by generative modelling of
interactional dynamics",
        BOOKTITLE = CVPR4HB09,
        YEAR = "2009",
        PAGES = "103-109",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382050"}

@inproceedings{bb387989,
        AUTHOR = "Chen, J.B. and Zhang, S.Q.",
        TITLE = "Manifold learning-based phoneme recognition",
        BOOKTITLE = IASP09,
        YEAR = "2009",
        PAGES = "308-312",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382051"}

@inproceedings{bb387990,
        AUTHOR = "Mahdhaoui, A. and Chetouani, M. and Zong, C.",
        TITLE = "Motherese detection based on segmental and supra-segmental features",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382052"}

@inproceedings{bb387991,
        AUTHOR = "Zeng, Z. and Li, X. and Ma, X.H. and Ji, Q.A.",
        TITLE = "Adaptive context recognition based on audio signal",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382053"}

@inproceedings{bb387992,
        AUTHOR = "Luo, L. and Lu, P.F. and Wang, Z.F.",
        TITLE = "A real-time accompaniment system based on sung voice recognition",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382054"}

@inproceedings{bb387993,
        AUTHOR = "Pesarin, A. and Cristani, M. and Murino, V. and Drioli, C. and Perina, A. and Tavano, A.",
        TITLE = "A statistical signature for automatic dialogue classification",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382055"}

@inproceedings{bb387994,
        AUTHOR = "Choi, H. and Gutierrez Osuna, R. and Choi, S.J. and Choe, Y.",
        TITLE = "Kernel oriented discriminant analysis for speaker-independent phoneme
spaces",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382056"}

@inproceedings{bb387995,
        AUTHOR = "Terry, L. and Katsaggelos, A.K.",
        TITLE = "A phone-viseme dynamic Bayesian network for audio-visual automatic
speech recognition",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382057"}

@inproceedings{bb387996,
        AUTHOR = "Krajewski, J. and Batliner, A. and Wieland, R.",
        TITLE = "Multiple classifier applied on predicting microsleep from speech",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382058"}

@inproceedings{bb387997,
        AUTHOR = "Banerjee, P. and Garg, G. and Mitra, P. and Basu, A.",
        TITLE = "Application of triphone clustering in acoustic modeling for continuous
speech recognition in Bengali",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382059"}

@inproceedings{bb387998,
        AUTHOR = "Bouzid, A. and Ellouze, N.",
        TITLE = "Voicing Detection in Noisy Speech Signal",
        BOOKTITLE = ICISP08,
        YEAR = "2008",
        PAGES = "544-551",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382060"}

@inproceedings{bb387999,
        AUTHOR = "Turkmen, H.I. and Karsligil, M.E.",
        TITLE = "Reconstruction of Dysphonic Speech by MELP",
        BOOKTITLE = CIARP08,
        YEAR = "2008",
        PAGES = "767-774",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT382061"}