@article{bb367800,
AUTHOR = "Hsiao, R. and Can, D. and Ng, T. and Travadi, R. and Ghoshal, A.",
TITLE = "Online Automatic Speech Recognition With Listen, Attend and Spell
Model",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1889-1893",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361965"}
@article{bb367801,
AUTHOR = "Qiu, J.Y. and Wang, X.C. and Fua, P. and Tao, D.C.",
TITLE = "Matching Seqlets: An Unsupervised Approach for Locality Preserving
Sequence Matching",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "2",
MONTH = "February",
PAGES = "745-752",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361966"}
@article{bb367802,
AUTHOR = "de Souza, D.B. and Bakri, K.J. and de Souza Ferreira, F. and Inacio, J.",
TITLE = "Multitaper-Mel Spectrograms for Keyword Spotting",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2028-2032",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361967"}
@inproceedings{bb367803,
AUTHOR = "Ezzine, A. and Satori, H. and Hamidi, M. and Satori, K.",
TITLE = "Moroccan Dialect Speech Recognition System Based on CMU SphinxTools",
BOOKTITLE = ISCV20,
YEAR = "2020",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361968"}
@inproceedings{bb367804,
AUTHOR = "Shahin, M. and Ji, J.X. and Ahmed, B.",
TITLE = "One-Class SVMs Based Pronunciation Verification Approach",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2881-2886",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361969"}
@inproceedings{bb367805,
AUTHOR = "Addarrazi, I. and Satori, H. and Satori, K.",
TITLE = "Amazigh audiovisual speech recognition system design",
BOOKTITLE = ISCV17,
YEAR = "2017",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361970"}
@inproceedings{bb367806,
AUTHOR = "Wu, C. and Ng, R.W.M. and Torralba, O.S. and Hain, T.",
TITLE = "Analysing acoustic model changes for active learning in automatic
speech recognition",
BOOKTITLE = WSSIP17,
YEAR = "2017",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361971"}
@inproceedings{bb367807,
AUTHOR = "Asadullah and Shaukat, A. and Ali, H. and Akram, U.",
TITLE = "Automatic Urdu Speech Recognition using Hidden Markov Model",
BOOKTITLE = ICIVC16,
YEAR = "2016",
PAGES = "135-139",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361972"}
@inproceedings{bb367808,
AUTHOR = "Conka, D. and Viszlay, P. and Juhar, J.",
TITLE = "Fuzzy clustering in HMM-based triphone classes of 2DLDA in Slovak
LVCSR",
BOOKTITLE = WSSIP16,
YEAR = "2016",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361973"}
@inproceedings{bb367809,
AUTHOR = "Kacur, J. and Kozicka, R. and Vargic, R.",
TITLE = "Semi-tight covariance matrices implementation in MASPER HMM training
procedure",
BOOKTITLE = WSSIP16,
YEAR = "2016",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361974"}
@inproceedings{bb367810,
AUTHOR = "Kacur, J. and Trnovsky, T. and Vargic, R.",
TITLE = "Discriminative training of HMM using MASPER procedure",
BOOKTITLE = WSSIP15,
YEAR = "2015",
PAGES = "93-96",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361975"}
@inproceedings{bb367811,
AUTHOR = "Perez Maldonado, Y. and Caballero Morales, S.O. and Cruz Ortega, R.O.",
TITLE = "GA Approaches to HMM Optimization for Automatic Speech Recognition",
BOOKTITLE = MCPR12,
YEAR = "2012",
PAGES = "313-322",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361976"}
@inproceedings{bb367812,
AUTHOR = "Swietojanski, P. and Wielgat, R. and Zielinski, T.",
TITLE = "Automatic Selection of Pareto-Optimal Topologies of Hidden Markov
Models Using Multicriteria Evolutionary Algorithms",
BOOKTITLE = EvoIASP11,
YEAR = "2011",
PAGES = "224-233",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361977"}
@inproceedings{bb367813,
AUTHOR = "Ravinder, K.",
TITLE = "Comparison of HMM and DTW for Isolated Word Recognition System of
Punjabi Language",
BOOKTITLE = CIARP10,
YEAR = "2010",
PAGES = "244-252",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361978"}
@inproceedings{bb367814,
AUTHOR = "Duan, Q.S. and Kang, S.Y. and Wu, Z.Y. and Cai, L.H. and Shuang, Z.W. and Qin, Y.",
TITLE = "Comparison of Syllable/Phone HMM Based Mandarin TTS",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "4496-4499",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361979"}
@inproceedings{bb367815,
AUTHOR = "Kacur, J. and Rozinaj, G.",
TITLE = "Adding Voicing Features into Speech Recognition Based on HMM in Slovak",
BOOKTITLE = WSSIP09,
YEAR = "2009",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361980"}
@inproceedings{bb367816,
AUTHOR = "Kruger, S.E. and Schaffoner, M. and Katz, M. and Andelic, E. and Wendemuth, A.",
TITLE = "Mixture of Support Vector Machines for HMM based Speech Recognition",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "IV: 326-329",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361981"}
@inproceedings{bb367817,
AUTHOR = "Andelic, E. and Schaffoner, M. and Katz, M. and Kruger, S.E.",
TITLE = "A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants
as Acoustic Models",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "II: 1158-1161",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361982"}
@inproceedings{bb367818,
AUTHOR = "Demirekler, M. and Karahan, F. and Ciloglu, T.",
TITLE = "Fusing length and voicing information, and HMM decision using a
Bayesian causal tree against insufficient training data",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol III: 102-105",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361983"}
@inproceedings{bb367819,
AUTHOR = "Steidl, S. and Stemmer, G. and Hacker, C. and Noth, E. and Niemann, H.",
TITLE = "Improving Children's Speech Recognition by HMM Interpolation with an
Adults' Speech Recognizer",
BOOKTITLE = DAGM03,
YEAR = "2003",
PAGES = "600-607",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361984"}
@inproceedings{bb367820,
AUTHOR = "Nouza, J.",
TITLE = "Feature selection methods for hidden Markov model-based speech
recognition",
BOOKTITLE = ICPR96,
YEAR = "1996",
PAGES = "II: 186-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361985"}
@inproceedings{bb367821,
AUTHOR = "Rieck, S. and Schukat Talamazzini, E.G. and Niemann, H.",
TITLE = "Speaker adaptation using semi-continuous hidden Markov models",
BOOKTITLE = ICPR92,
YEAR = "1992",
PAGES = "III:541-544",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024hmm2.html#TT361986"}
@article{bb367822,
AUTHOR = "Wu, J.X. and Chan, C.",
TITLE = "Isolated word recognition by neural network models with
cross-correlation coefficients for speech dynamics",
JOURNAL = PAMI,
VOLUME = "15",
YEAR = "1993",
NUMBER = "11",
MONTH = "November",
PAGES = "1174-1185",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361987"}
@article{bb367823,
AUTHOR = "Chen, W.Y. and Liao, Y.F. and Chen, S.H.",
TITLE = "Speech recognition with hierarchical recurrent neural networks",
JOURNAL = PR,
VOLUME = "28",
YEAR = "1995",
NUMBER = "6",
MONTH = "June",
PAGES = "795-805",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361988"}
@article{bb367824,
AUTHOR = "Lee, T. and Ching, P.C. and Chan, L.W.",
TITLE = "Isolated word recognition using modular recurrent neural networks",
JOURNAL = PR,
VOLUME = "31",
YEAR = "1998",
NUMBER = "6",
MONTH = "June",
PAGES = "751-760",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361989"}
@article{bb367825,
AUTHOR = "Stavrakoudis, D.G. and Theocharis, J.B.",
TITLE = "Pipelined Recurrent Fuzzy Neural Networks for Nonlinear Adaptive Speech
Prediction",
JOURNAL = SMC-B,
VOLUME = "37",
YEAR = "2007",
NUMBER = "5",
MONTH = "October",
PAGES = "1305-1320",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361990"}
@article{bb367826,
AUTHOR = "Kay, S.",
TITLE = "A New Approach to Fourier Synthesis With Application to Neural Encoding
and Speech Classification",
JOURNAL = SPLetters,
VOLUME = "17",
YEAR = "2010",
NUMBER = "10",
MONTH = "October",
PAGES = "855-858",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361991"}
@article{bb367827,
AUTHOR = "Kay, S.",
TITLE = "A New Proof of the Neyman-Pearson Theorem Using the EEF and the
Vindication of Sir R. Fisher",
JOURNAL = SPLetters,
VOLUME = "19",
YEAR = "2012",
NUMBER = "8",
MONTH = "August",
PAGES = "451-454",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361992"}
@article{bb367828,
AUTHOR = "Scanzio, S. and Cumani, S. and Gemello, R. and Mana, F. and Laface, P.",
TITLE = "Parallel implementation of Artificial Neural Network training for
speech recognition",
JOURNAL = PRL,
VOLUME = "31",
YEAR = "2010",
NUMBER = "11",
MONTH = "August",
PAGES = "1302-1309",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361993"}
@article{bb367829,
AUTHOR = "Siniscalchi, S.M. and Yu, D. and Deng, L. and Lee, C.H.",
TITLE = "Speech Recognition Using Long-Span Temporal Patterns in a Deep Network
Model",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "3",
MONTH = "March",
PAGES = "201-204",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361994"}
@article{bb367830,
AUTHOR = "Hutchinson, B. and Deng, L. and Yu, D.",
TITLE = "Tensor Deep Stacking Networks",
JOURNAL = PAMI,
VOLUME = "35",
YEAR = "2013",
NUMBER = "8",
PAGES = "1944-1957",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361995"}
@article{bb367831,
AUTHOR = "Bengio, Y. and Courville, A. and Vincent, P.",
TITLE = "Representation Learning: A Review and New Perspectives",
JOURNAL = PAMI,
VOLUME = "35",
YEAR = "2013",
NUMBER = "8",
PAGES = "1798-1828",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361996"}
@article{bb367832,
AUTHOR = "Swietojanski, P. and Ghoshal, A. and Renals, S.",
TITLE = "Convolutional Neural Networks for Distant Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "21",
YEAR = "2014",
NUMBER = "9",
MONTH = "September",
PAGES = "1120-1124",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361997"}
@article{bb367833,
AUTHOR = "Espi, M. and Fujimoto, M. and Nakatani, T.",
TITLE = "Acoustic Event Detection in Speech Overlapping Scenarios Based on
High-Resolution Spectral Input and Deep Learning",
JOURNAL = IEICE,
VOLUME = "E98-D",
YEAR = "2015",
NUMBER = "10",
MONTH = "October",
PAGES = "1799-1807",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361998"}
@article{bb367834,
AUTHOR = "Richardson, F. and Reynolds, D. and Dehak, N.",
TITLE = "Deep Neural Network Approaches to Speaker and Language Recognition",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "10",
MONTH = "October",
PAGES = "1671-1675",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT361999"}
@article{bb367835,
AUTHOR = "Trentin, E.",
TITLE = "Maximum-likelihood normalization of features increases the robustness
of neural-based spoken human-computer interaction",
JOURNAL = PRL,
VOLUME = "66",
YEAR = "2015",
NUMBER = "1",
PAGES = "71-80",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362000"}
@article{bb367836,
AUTHOR = "Lee, H.Y. and Cho, J.W. and Kim, M. and Park, H.M.",
TITLE = "DNN-Based Feature Enhancement Using DOA-Constrained ICA for Robust
Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "8",
MONTH = "August",
PAGES = "1091-1095",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362001"}
@article{bb367837,
AUTHOR = "Sangeetha, J. and Jothilakshmi, S.",
TITLE = "Automatic continuous speech recogniser for Dravidian languages using
the auto associative neural network",
JOURNAL = IJCVR,
VOLUME = "6",
YEAR = "2016",
NUMBER = "1-2",
PAGES = "113-126",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362002"}
@article{bb367838,
AUTHOR = "Fredes, J. and Novoa, J. and King, S. and Stern, R.M. and Yoma, N.B.",
TITLE = "Locally Normalized Filter Banks Applied to Deep Neural-Network-Based
Robust Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "4",
MONTH = "April",
PAGES = "377-381",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362003"}
@article{bb367839,
AUTHOR = "Shahnawazuddin, S. and Sinha, R. and Pradhan, G.",
TITLE = "Pitch-Normalized Acoustic Features for Robust Children's Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "8",
MONTH = "August",
PAGES = "1128-1132",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362004"}
@article{bb367840,
AUTHOR = "Gosztolya, G. and Toth, L.",
TITLE = "DNN-Based Feature Extraction for Conflict Intensity Estimation From
Speech",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "12",
MONTH = "December",
PAGES = "1837-1841",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362005"}
@inproceedings{bb367841,
AUTHOR = "Gosztolya, G. and Banhalmi, A. and Toth, L.",
TITLE = "Using One-Class Classification Techniques in the Anti-phoneme Problem",
BOOKTITLE = IbPRIA09,
YEAR = "2009",
PAGES = "433-440",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362006"}
@article{bb367842,
AUTHOR = "Kim, M. and Kim, H.",
TITLE = "Integrated neural network model for identifying speech acts,
predicators, and sentiments of dialogue utterances",
JOURNAL = PRL,
VOLUME = "101",
YEAR = "2018",
NUMBER = "1",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362007"}
@article{bb367843,
AUTHOR = "Affonso, E.T. and Rosa, R.L. and Rodriguez, D.Z.",
TITLE = "Speech Quality Assessment Over Lossy Transmission Channels Using Deep
Belief Networks",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "1",
MONTH = "January",
PAGES = "70-74",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362008"}
@article{bb367844,
AUTHOR = "Kim, H.G. and Lee, H. and Kim, G. and Oh, S.H. and Lee, S.Y.",
TITLE = "Rescoring of N-Best Hypotheses Using Top-Down Selective Attention for
Automatic Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "2",
MONTH = "February",
PAGES = "199-203",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362009"}
@article{bb367845,
AUTHOR = "Kaushik, L. and Sangwan, A. and Hansen, J.H.L.",
TITLE = "Speech Activity Detection in Naturalistic Audio Environments:
Fearless Steps Apollo Corpus",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "9",
MONTH = "September",
PAGES = "1290-1294",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362010"}
@article{bb367846,
AUTHOR = "Heracleous, P. and Even, J. and Sugaya, F. and Hashimoto, M. and Yoneyama, A.",
TITLE = "Exploiting alternative acoustic sensors for improved noise robustness
in speech communication",
JOURNAL = PRL,
VOLUME = "112",
YEAR = "2018",
PAGES = "191-197",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362011"}
@article{bb367847,
AUTHOR = "Takahashi, N. and Gygli, M. and Van Gool, L.J.",
TITLE = "AENet: Learning Deep Audio Features for Video Analysis",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "3",
MONTH = "March",
PAGES = "513-524",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362012"}
@article{bb367848,
AUTHOR = "Cho, B.J. and Lee, J. and Park, H.",
TITLE = "A Beamforming Algorithm Based on Maximum Likelihood of a Complex
Gaussian Distribution With Time-Varying Variances for Robust Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "9",
MONTH = "September",
PAGES = "1398-1402",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362013"}
@article{bb367849,
AUTHOR = "Gundogdu, B. and Yusuf, B. and Saraclar, M.",
TITLE = "Generative RNNs for OOV Keyword Search",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "1",
MONTH = "January",
PAGES = "124-128",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362014"}
@article{bb367850,
AUTHOR = "Seshadri, S. and Rasanen, O.",
TITLE = "SylNet: An Adaptable End-to-End Syllable Count Estimator for Speech",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "9",
MONTH = "September",
PAGES = "1359-1363",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362015"}
@article{bb367851,
AUTHOR = "Last, P. and Engelbrecht, H.A. and Kamper, H.",
TITLE = "Unsupervised Feature Learning for Speech Using Correspondence and
Siamese Networks",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "421-425",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362016"}
@article{bb367852,
AUTHOR = "John Wesley, R. and Nayeemulla Khan, A. and Shahina, A.",
TITLE = "Phoneme classification in reconstructed phase space with
convolutional neural networks",
JOURNAL = PRL,
VOLUME = "135",
YEAR = "2020",
PAGES = "299-306",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362017"}
@article{bb367853,
AUTHOR = "Phan, H. and McLoughlin, I.V. and Pham, L. and Chen, O.Y. and Koch, P. and de Vos, M. and Mertins, A.",
TITLE = "Improving GANs for Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1700-1704",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362018"}
@article{bb367854,
AUTHOR = "Wei, W. and Wang, Z. and Mao, X.L. and Zhou, G.Y. and Zhou, P. and Jiang, S.",
TITLE = "Position-aware self-attention based neural sequence labeling",
JOURNAL = PR,
VOLUME = "110",
YEAR = "2021",
PAGES = "107636",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362019"}
@article{bb367855,
AUTHOR = "Gu, R.Z. and Zhang, S.X. and Zou, Y.X. and Yu, D.",
TITLE = "Complex Neural Spatial Filter: Enhancing Multi-Channel Target Speech
Separation in Complex Domain",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1370-1374",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362020"}
@article{bb367856,
AUTHOR = "Li, Y.X. and Wang, W. and Liu, M. and Jiang, Z.J. and He, Q.H.",
TITLE = "Speaker Clustering by Co-Optimizing Deep Representation Learning and
Cluster Estimation",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "3377-3387",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362021"}
@article{bb367857,
AUTHOR = "Esmaeilpour, M. and Chaalia, N. and Cardinal, P.",
TITLE = "RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text
Adversarial Attacks",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1998-2002",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362022"}
@article{bb367858,
AUTHOR = "Tian, J.C. and Yu, J.W. and Weng, C. and Zou, Y.X. and Yu, D.",
TITLE = "Improving Mandarin End-to-End Speech Recognition With Word N-Gram
Language Model",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "812-816",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362023"}
@article{bb367859,
AUTHOR = "Mai, S.J. and Hu, H.F. and Xing, S.L.",
TITLE = "A Unimodal Representation Learning and Recurrent Decomposition Fusion
Structure for Utterance-Level Multimodal Embedding Learning",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "2488-2501",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362024"}
@article{bb367860,
AUTHOR = "Yang, R. and Cheng, G.F. and Zhang, P.Y. and Yan, Y.H.",
TITLE = "An E2E-ASR-Based Iteratively-Trained Timestamp Estimator",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1654-1658",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362025"}
@article{bb367861,
AUTHOR = "Muralikrishna, H. and Aroor Dinesh, D.",
TITLE = "Spoken language identification in unseen channel conditions using
modified within-sample similarity loss",
JOURNAL = PRL,
VOLUME = "158",
YEAR = "2022",
PAGES = "16-23",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362026"}
@article{bb367862,
AUTHOR = "Nasir, M. and Baucom, B. and Bryan, C. and Narayanan, S. and Georgiou, P.",
TITLE = "Modeling Vocal Entrainment in Conversational Speech Using Deep
Unsupervised Learning",
JOURNAL = AffCom,
VOLUME = "13",
YEAR = "2022",
NUMBER = "3",
MONTH = "July",
PAGES = "1651-1663",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362027"}
@article{bb367863,
AUTHOR = "Lian, Z. and Chen, L. and Sun, L. and Liu, B. and Tao, J.H.",
TITLE = "GCNet: Graph Completion Network for Incomplete Multimodal Learning in
Conversation",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "7",
MONTH = "July",
PAGES = "8419-8432",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362028"}
@article{bb367864,
AUTHOR = "Sun, H.R. and Wang, D. and Li, L. and Chen, C. and Zheng, T.F.",
TITLE = "Random Cycle Loss and Its Application to Voice Conversion",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "8",
MONTH = "August",
PAGES = "10331-10345",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362029"}
@article{bb367865,
AUTHOR = "Li, L. and Wang, A. and Xu, M. and Dong, Y.F. and Li, X.",
TITLE = "Abductive natural language inference by interactive model with
structural loss",
JOURNAL = PRL,
VOLUME = "177",
YEAR = "2024",
PAGES = "82-88",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362030"}
@article{bb367866,
AUTHOR = "Wang, Q.Q. and Lee, K.A.",
TITLE = "Cosine Scoring With Uncertainty for Neural Speaker Embedding",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "845-849",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362031"}
@article{bb367867,
AUTHOR = "Singh, S. and Steinmetz, C.J. and Benetos, E. and Phan, H. and Stowell, D.",
TITLE = "ATGNN: Audio Tagging Graph Neural Network",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "825-829",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362032"}
@article{bb367868,
AUTHOR = "Wang, S. and Ni, L. and Zhang, Z. and Li, X.X. and Zheng, X. and Liu, J.",
TITLE = "Multimodal prediction of student performance: A fusion of signed
graph neural networks and large language models",
JOURNAL = PRL,
VOLUME = "181",
YEAR = "2024",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362033"}
@article{bb367869,
AUTHOR = "Song, Y.H. and Guo, L. and Man, M. and Wu, Y.X.",
TITLE = "The spiking neural network based on fMRI for speech recognition",
JOURNAL = PR,
VOLUME = "155",
YEAR = "2024",
PAGES = "110672",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362034"}
@article{bb367870,
AUTHOR = "Ma, D. and Yue, X.H. and Ao, J. and Gao, X.X. and Li, H.Z.",
TITLE = "Text-Guided HuBERT: Self-Supervised Speech Pre-Training via
Generative Adversarial Networks",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2055-2059",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362035"}
@article{bb367871,
AUTHOR = "Kim, S.S. and Lee, D. and Kang, J.Y. and Jeong, M. and Kim, N.S.",
TITLE = "Sampling-Based Pruned Knowledge Distillation for Training Lightweight
RNN-T",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "631-635",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362036"}
@inproceedings{bb367872,
AUTHOR = "Burchi, M. and Timofte, R.",
TITLE = "Audio-Visual Efficient Conformer for Robust Speech Recognition",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "2257-2266",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362037"}
@inproceedings{bb367873,
AUTHOR = "Aitoulghazi, O. and Jaafari, A. and Mourhir, A.",
TITLE = "DarSpeech: An Automatic Speech Recognition System for the Moroccan
Dialect",
BOOKTITLE = ISCV22,
YEAR = "2022",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362038"}
@inproceedings{bb367874,
AUTHOR = "Zhai, M.E. and Dong, L.H. and Qin, Y. and Yu, F.F.",
TITLE = "The Research of Chain Model Based on CNN-TDNNF in Yulin Dialect
Speech Recognition",
BOOKTITLE = ICIVC22,
YEAR = "2022",
PAGES = "883-888",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362039"}
@inproceedings{bb367875,
AUTHOR = "Vedvyasan, K. and Nathwani, K. and Hegde, R.M.",
TITLE = "Group Delay based Methods for Detection and Recognition of Whispered
Speech",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "499-505",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362040"}
@inproceedings{bb367876,
AUTHOR = "Toufa, A.S. and Kotropoulos, C.",
TITLE = "Digit Recognition Applied to Reconstructed Audio Signals Using Deep
Learning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3050-3057",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362041"}
@inproceedings{bb367877,
AUTHOR = "Chakraborty, J. and Chakraborty, B. and Bhattacharya, U.",
TITLE = "Dense Recognition of Spoken Languages",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "9674-9681",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362042"}
@inproceedings{bb367878,
AUTHOR = "Ghezaiel, W. and Brun, L. and LEZORAY, O.",
TITLE = "Hybrid Network For End-To-End Text-Independent Speaker Identification",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "2352-2359",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362043"}
@inproceedings{bb367879,
AUTHOR = "Zhou, P.L. and Huang, Z.Q. and Liu, F.L. and Zou, Y.X.",
TITLE = "PIN: A Novel Parallel Interactive Network for Spoken Language
Understanding",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "2950-2957",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362044"}
@inproceedings{bb367880,
AUTHOR = "Zhu, B.L. and Chen, X.B. and Chen, T.Y. and Zhu, J.R.",
TITLE = "Experiment Research on Mobile Terminal Image Scene Recognition Based
on optimization",
BOOKTITLE = CVIDL20,
YEAR = "2020",
PAGES = "70-75",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362045"}
@inproceedings{bb367881,
AUTHOR = "Wang, P.",
TITLE = "Research and Design of Smart Home Speech Recognition System Based on
Deep Learning",
BOOKTITLE = CVIDL20,
YEAR = "2020",
PAGES = "218-221",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362046"}
@inproceedings{bb367882,
AUTHOR = "Wang, L.",
TITLE = "A Speech Content Retrieval Model Based on Integrated Neural Network
for Natural Language Description",
BOOKTITLE = CVIDL20,
YEAR = "2020",
PAGES = "532-535",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362047"}
@inproceedings{bb367883,
AUTHOR = "Scharenborg, O. and van der Gouw, N. and Larson, M. and Marchiori, E.",
TITLE = "The Representation of Speech in Deep Neural Networks",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "II:194-205",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362048"}
@inproceedings{bb367884,
AUTHOR = "Roth, J. and Chaudhuri, S. and Klejch, O. and Marvin, R. and Gallagher, A. and Kaver, L. and Ramaswamy, S. and Stopczynski, A. and Schmid, C. and Xi, Z. and Pantofaru, C.",
TITLE = "Supplementary Material: AVA-ActiveSpeaker:
An Audio-Visual Dataset for Active Speaker Detection",
BOOKTITLE = MMVAMTC19,
YEAR = "2019",
PAGES = "3718-3722",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362049"}
@inproceedings{bb367885,
AUTHOR = "Wang, F. and Chen, W. and Yang, Z. and Xu, B.",
TITLE = "Self-Attention Based Network for Punctuation Restoration",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2803-2808",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362050"}
@inproceedings{bb367886,
AUTHOR = "Tokozume, Y. and Ushiku, Y. and Harada, T.",
TITLE = "Between-Class Learning for Image Classification",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "5486-5494",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362051"}
@inproceedings{bb367887,
AUTHOR = "Smirnov, E. and Ivanova, E. and Melnikov, A. and Kalinovskiy, I. and Oleinik, A. and Luckyanets, E.",
TITLE = "Hard Example Mining with Auxiliary Embeddings",
BOOKTITLE = DFW18,
YEAR = "2018",
PAGES = "37-3709",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362052"}
@inproceedings{bb367888,
AUTHOR = "Ding, K. and Luo, N. and Xu, Y. and Ke, D. and Su, K.",
TITLE = "Mutual-optimization Towards Generative Adversarial Networks For
Robust Speech Recognition",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2699-2704",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362053"}
@inproceedings{bb367889,
AUTHOR = "Li, C. and Zhu, L. and Xu, S. and Gao, P. and Xu, B.",
TITLE = "Recurrent Neural Network Based Small-footprint Wake-up-word Speech
Recognition System with a Score Calibration Method",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "3222-3227",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362054"}
@inproceedings{bb367890,
AUTHOR = "Li, C. and Zhu, L. and Xu, S. and Gao, P. and Xu, B.",
TITLE = "Compression of Acoustic Model via Knowledge Distillation and Pruning",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2785-2790",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362055"}
@inproceedings{bb367891,
AUTHOR = "Zhang, S. and Liu, W. and Qin, Y.",
TITLE = "Wake-up-word spotting using end-to-end deep neural network system",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "2878-2883",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362056"}
@inproceedings{bb367892,
AUTHOR = "Zhang, S.L. and Qin, Y.",
TITLE = "Rapid feature space MLLR speaker adaptation for deep neural network
acoustic modeling",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "2889-2894",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362057"}
@inproceedings{bb367893,
AUTHOR = "Zheng, H. and Cai, W. and Zhou, T.Y. and Zhang, S.L. and Li, M.",
TITLE = "Text-independent voice conversion using deep neural network based
phonetic level features",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "2872-2877",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362058"}
@inproceedings{bb367894,
AUTHOR = "Zhang, B. and Gan, Y.Q. and Song, Y. and Tang, B.L.",
TITLE = "Application of pronunciation knowledge on phoneme recognition by LSTM
neural network",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "2906-2911",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362059"}
@inproceedings{bb367895,
AUTHOR = "Garcia, F. and Sanchis, E. and Hurtado, L.F. and Segarra, E.",
TITLE = "Adaptive Training for Robust Spoken Language Understanding",
BOOKTITLE = CIARP15,
YEAR = "2015",
PAGES = "519-526",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362060"}
@inproceedings{bb367896,
AUTHOR = "Pastor, J. and Hurtado, L.F. and Segarra, E. and Sanchis, E.",
TITLE = "Language Modelization and Categorization for Voice-Activated QA",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "475-482",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362061"}
@inproceedings{bb367897,
AUTHOR = "Garcia, F. and Hurtado, L.F. and Sanchis, E. and Segarra, E.",
TITLE = "An Active Learning Approach for Statistical Spoken Language
Understanding",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "565-572",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362062"}
@inproceedings{bb367898,
AUTHOR = "Hurtado, L.F. and Griol, D. and Sanchis, E. and Segarra, E.",
TITLE = "A Statistical User Simulation Technique for the Improvement of a Spoken
Dialog System",
BOOKTITLE = CIARP07,
YEAR = "2007",
PAGES = "743-752",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362063"}
@inproceedings{bb367899,
AUTHOR = "Griol, D. and Hurtado, L.F. and Segarra, E. and Sanchis, E.",
TITLE = "A Dialog Management Methodology Based on Neural Networks and Its
Application to Different Domains",
BOOKTITLE = CIARP08,
YEAR = "2008",
PAGES = "643-650",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT362064"}
Last update:Oct 6, 2025 at 14:07:43