@article{bb387800,
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#TT381863"}
@article{bb387801,
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#TT381864"}
@article{bb387802,
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#TT381865"}
@article{bb387803,
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#TT381866"}
@article{bb387804,
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#TT381867"}
@article{bb387805,
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#TT381868"}
@article{bb387806,
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#TT381869"}
@inproceedings{bb387807,
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#TT381870"}
@article{bb387808,
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#TT381871"}
@article{bb387809,
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#TT381872"}
@article{bb387810,
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#TT381873"}
@article{bb387811,
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#TT381874"}
@article{bb387812,
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#TT381875"}
@article{bb387813,
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#TT381876"}
@article{bb387814,
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#TT381877"}
@article{bb387815,
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#TT381878"}
@article{bb387816,
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#TT381879"}
@article{bb387817,
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#TT381880"}
@article{bb387818,
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#TT381881"}
@article{bb387819,
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#TT381882"}
@article{bb387820,
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#TT381883"}
@article{bb387821,
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#TT381884"}
@article{bb387822,
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#TT381885"}
@article{bb387823,
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#TT381886"}
@article{bb387824,
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#TT381887"}
@article{bb387825,
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#TT381888"}
@article{bb387826,
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#TT381889"}
@article{bb387827,
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#TT381890"}
@article{bb387828,
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#TT381891"}
@article{bb387829,
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#TT381892"}
@article{bb387830,
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#TT381893"}
@article{bb387831,
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#TT381894"}
@article{bb387832,
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#TT381895"}
@article{bb387833,
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#TT381896"}
@article{bb387834,
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#TT381897"}
@article{bb387835,
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#TT381898"}
@article{bb387836,
AUTHOR = "Lee, E. and Chae, J. and Park, S. and Shin, J.W.",
TITLE = "R3VQ: Redundancy-Reduced Residual Vector Quantization for Low-Bitrate
Neural Speech Coding",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "693-697",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT381899"}
@inproceedings{bb387837,
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#TT381900"}
@inproceedings{bb387838,
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#TT381901"}
@inproceedings{bb387839,
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#TT381902"}
@inproceedings{bb387840,
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#TT381903"}
@inproceedings{bb387841,
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#TT381904"}
@inproceedings{bb387842,
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#TT381905"}
@inproceedings{bb387843,
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#TT381906"}
@inproceedings{bb387844,
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#TT381907"}
@inproceedings{bb387845,
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#TT381908"}
@inproceedings{bb387846,
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#TT381909"}
@inproceedings{bb387847,
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#TT381910"}
@inproceedings{bb387848,
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#TT381911"}
@inproceedings{bb387849,
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#TT381912"}
@inproceedings{bb387850,
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#TT381913"}
@inproceedings{bb387851,
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#TT381914"}
@inproceedings{bb387852,
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#TT381915"}
@inproceedings{bb387853,
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#TT381916"}
@inproceedings{bb387854,
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#TT381917"}
@inproceedings{bb387855,
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#TT381918"}
@inproceedings{bb387856,
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#TT381919"}
@inproceedings{bb387857,
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#TT381920"}
@inproceedings{bb387858,
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#TT381921"}
@inproceedings{bb387859,
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#TT381922"}
@inproceedings{bb387860,
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#TT381923"}
@inproceedings{bb387861,
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#TT381924"}
@inproceedings{bb387862,
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#TT381925"}
@inproceedings{bb387863,
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#TT381926"}
@inproceedings{bb387864,
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#TT381927"}
@inproceedings{bb387865,
AUTHOR = "He, H.Y. and Wen, C.Y.",
TITLE = "ART2-based multiple MLPs neural network for speaker-independent
recognition of isolated words",
BOOKTITLE = ICPR92,
YEAR = "1992",
PAGES = "II:590-593",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024snn1.html#TT381928"}
@article{bb387866,
AUTHOR = "de Mori, R. and Laface, P. and Makhonine, V.A. and Mezzalama, M.",
TITLE = "A syntactic procedure for the recognition of glottal pulses in
continuous speech",
JOURNAL = PR,
VOLUME = "9",
YEAR = "1977",
NUMBER = "4",
PAGES = "181-189",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381929"}
@article{bb387867,
AUTHOR = "de Mori, R. and Giordano, G.",
TITLE = "Algorithms for syllabic hypothesization in continuous speech",
JOURNAL = PR,
VOLUME = "14",
YEAR = "1981",
NUMBER = "1-6",
PAGES = "245-260",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381930"}
@article{bb387868,
AUTHOR = "Pal, S.K. and Datta, A.K. and Majumder, D.D.",
TITLE = "A self-supervised vowel recognition system",
JOURNAL = PR,
VOLUME = "12",
YEAR = "1980",
NUMBER = "1",
PAGES = "27-34",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381931"}
@article{bb387869,
AUTHOR = "Pathak, A. and Pal, S.K.",
TITLE = "On the convergence of 'A self-supervised vowel recognition system'",
JOURNAL = PR,
VOLUME = "20",
YEAR = "1987",
NUMBER = "2",
PAGES = "237-244",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381932"}
@article{bb387870,
AUTHOR = "Howard, J.H.",
TITLE = "Feature selection in human auditory perception",
JOURNAL = PR,
VOLUME = "15",
YEAR = "1982",
NUMBER = "5",
PAGES = "397-403",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381933"}
@article{bb387871,
AUTHOR = "Thomason, M.G. and Granum, E. and Blake, R.E.",
TITLE = "Experiments in dynamic programming inference of Markov networks with
strings representing speech data",
JOURNAL = PR,
VOLUME = "19",
YEAR = "1986",
NUMBER = "5",
PAGES = "343-352",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381934"}
@article{bb387872,
AUTHOR = "Tanaka, E. and Toyama, T. and Kawai, S.",
TITLE = "High speed error correction of phoneme sequences",
JOURNAL = PR,
VOLUME = "19",
YEAR = "1986",
NUMBER = "5",
PAGES = "407-412",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381935"}
@article{bb387873,
AUTHOR = "Hochberg, J. and Mniszewski, S.M. and Calleja, T. and Papcun, G.J.",
TITLE = "A default hierarchy for pronouncing English",
JOURNAL = PAMI,
VOLUME = "13",
YEAR = "1991",
NUMBER = "9",
MONTH = "September",
PAGES = "957-964",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381936"}
@article{bb387874,
AUTHOR = "Carlson, B.A. and Clements, M.A.",
TITLE = "A computationally compact divergence measure for speech processing",
JOURNAL = PAMI,
VOLUME = "13",
YEAR = "1991",
NUMBER = "12",
MONTH = "December",
PAGES = "1255-1260",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381937"}
@article{bb387875,
AUTHOR = "Tacer, B. and Loughlin, P.J.",
TITLE = "Non-stationary signal classification using the joint moments of
time-frequency distributions",
JOURNAL = PR,
VOLUME = "31",
YEAR = "1998",
NUMBER = "11",
MONTH = "November",
PAGES = "1635-1641",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381938"}
@article{bb387876,
AUTHOR = "Li, M. and McAllister, H.G. and Black, N.D. and de Perez, T.A.",
TITLE = "Wavelet-based nonlinear AGC method for hearing aid loudness
compensation",
JOURNAL = VISP,
VOLUME = "147",
YEAR = "2000",
NUMBER = "6",
MONTH = "December",
PAGES = "502-507",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381939"}
@article{bb387877,
AUTHOR = "Gray, P. and Hollier, M.P. and Massara, R.E.",
TITLE = "Non-intrusive speech-quality assessment using vocal-tract models",
JOURNAL = VISP,
VOLUME = "147",
YEAR = "2000",
NUMBER = "6",
MONTH = "December",
PAGES = "493-501",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381940"}
@article{bb387878,
AUTHOR = "Sarkar, S. and Poor, H.V.",
TITLE = "Multirate signal processing on finite fields",
JOURNAL = VISP,
VOLUME = "148",
YEAR = "2001",
NUMBER = "4",
MONTH = "August",
PAGES = "254-262",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381941"}
@article{bb387879,
AUTHOR = "Ding, Z.O. and McLoughlin, I.V. and Tan, E.C.",
TITLE = "Extension of proposal of standards for intelligibility tests of Chinese
speech: CDRT-tone",
JOURNAL = VISP,
VOLUME = "150",
YEAR = "2003",
NUMBER = "1",
MONTH = "February",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381942"}
@article{bb387880,
AUTHOR = "de Lamare, R.C. and Alcaim, A.",
TITLE = "Strategies to improve the performance of very low bit rate speech
coders and application to a variable rate 1.2 kb/s codec",
JOURNAL = VISP,
VOLUME = "152",
YEAR = "2005",
NUMBER = "1",
MONTH = "February",
PAGES = "74-86",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381943"}
@article{bb387881,
AUTHOR = "Vera Candeas, P. and Ruiz Reyes, N. and Rosa Zurera, M. and Lopez Ferreras, F. and Curpian Alonso, J.",
TITLE = "New matching pursuit based sinusoidal modelling method for audio coding",
JOURNAL = VISP,
VOLUME = "151",
YEAR = "2004",
NUMBER = "1",
MONTH = "February",
PAGES = "21-28",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381944"}
@inproceedings{bb387882,
AUTHOR = "Vera Candeas, P. and Ruiz Reyes, N. and Rosa Zurera, M. and Cuevas Martinez, J.C. and Lopez Ferreras, F.",
TITLE = "Adaptive Signal Models for Wide-Band Speech and Audio Compression",
BOOKTITLE = IbPRIA05,
YEAR = "2005",
PAGES = "II:571",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381945"}
@article{bb387883,
AUTHOR = "Li, C. and Li, S. and Zhang, D. and Chen, G.",
TITLE = "Cryptanalysis of a data securityp protection scheme for VoIP",
JOURNAL = VISP,
VOLUME = "153",
YEAR = "2006",
NUMBER = "1",
MONTH = "February",
PAGES = "1-10",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381946"}
@article{bb387884,
AUTHOR = "Sandler, M. and Black, D.",
TITLE = "Scalable audio coding for compression and loss resilient streaming",
JOURNAL = VISP,
VOLUME = "153",
YEAR = "2006",
NUMBER = "3",
MONTH = "June",
PAGES = "331-339",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381947"}
@article{bb387885,
AUTHOR = "Guido, R.C. and Pereira, J.C. and Slaets, J.F.W.",
TITLE = "Introduction to the Special Issue:
Advances on pattern recognition for speech and audio processing",
JOURNAL = PRL,
VOLUME = "28",
YEAR = "2007",
NUMBER = "11",
MONTH = "August",
PAGES = "1283-1284",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381948"}
@article{bb387886,
AUTHOR = "Frankel, J. and King, S.",
TITLE = "Factoring Gaussian precision matrices for linear dynamic models",
JOURNAL = PRL,
VOLUME = "28",
YEAR = "2007",
NUMBER = "16",
MONTH = "December",
PAGES = "2264-2272",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381949"}
@article{bb387887,
AUTHOR = "Arias Londono, J.D. and Godino Llorente, J.I. and Saenz Lechon, N. and Osma Ruiz, V. and Castellanos Dominguez, C.G.",
TITLE = "An improved method for voice pathology detection by means of a
HMM-based feature space transformation",
JOURNAL = PR,
VOLUME = "43",
YEAR = "2010",
NUMBER = "9",
MONTH = "September",
PAGES = "3100-3112",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381950"}
@article{bb387888,
AUTHOR = "Mahdi, A.E. and Picovici, D.",
TITLE = "New single-ended objective measure for non-intrusive speech quality
evaluation",
JOURNAL = SIViP,
VOLUME = "4",
YEAR = "2010",
NUMBER = "1",
MONTH = "March",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381951"}
@article{bb387889,
AUTHOR = "Guijarrubia, V.G. and Torres, M.I.",
TITLE = "Text- and speech-based phonotactic models for spoken language
identification of Basque and Spanish",
JOURNAL = PRL,
VOLUME = "31",
YEAR = "2010",
NUMBER = "6",
MONTH = "April",
PAGES = "523-532",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381952"}
@inproceedings{bb387890,
AUTHOR = "Guijarrubia, V.G. and Torres, M.I.",
TITLE = "Comparative Study of Several Phonotactic-Based Approaches to
Spanish-Basque Language Identification",
BOOKTITLE = CIARP08,
YEAR = "2008",
PAGES = "128-135",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381953"}
@inproceedings{bb387891,
AUTHOR = "Guijarrubia, V.G. and Torres, M.I.",
TITLE = "Phone-Segments Based Language Identification for Spanish, Basque and
English",
BOOKTITLE = CIARP07,
YEAR = "2007",
PAGES = "106-114",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381954"}
@inproceedings{bb387892,
AUTHOR = "Guijarrubia, V.G. and Torres, M.I.",
TITLE = "Language Identification Based on Phone Decoding for Basque and Spanish",
BOOKTITLE = IbPRIA07,
YEAR = "2007",
PAGES = "I: 233-240",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381955"}
@article{bb387893,
AUTHOR = "Shafiee, S. and Almasganj, F. and Vazirnezhad, B. and Jafari, A.",
TITLE = "A two-stage speech activity detection system considering fractal
aspects of prosody",
JOURNAL = PRL,
VOLUME = "31",
YEAR = "2010",
NUMBER = "9",
MONTH = "July",
PAGES = "936-948",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381956"}
@article{bb387894,
AUTHOR = "Yoon, J.Y. and Park, H.",
TITLE = "Improving the Speech Quality of VoIP by Packet Prioritization",
JOURNAL = SPLetters,
VOLUME = "18",
YEAR = "2011",
NUMBER = "12",
MONTH = "December",
PAGES = "725-728",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381957"}
@article{bb387895,
AUTHOR = "Dennis, J. and Tran, H.D. and Li, H.",
TITLE = "Spectrogram Image Feature for Sound Event Classification in Mismatched
Conditions",
JOURNAL = SPLetters,
VOLUME = "18",
YEAR = "2011",
NUMBER = "2",
MONTH = "February",
PAGES = "130-133",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381958"}
@article{bb387896,
AUTHOR = "Liang, Y. and Liu, X.L. and Lou, Y.H. and Shan, B.S.",
TITLE = "An improved noise-robust voice activity detector based on hidden
semi-Markov models",
JOURNAL = PRL,
VOLUME = "32",
YEAR = "2011",
NUMBER = "7",
MONTH = "May",
PAGES = "1044-1053",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381959"}
@inproceedings{bb387897,
AUTHOR = "Liu, X.L. and Liang, Y. and Lou, Y.H. and Li, H. and Shan, B.S.",
TITLE = "Noise-Robust Voice Activity Detector Based on Hidden Semi-Markov Models",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "81-84",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381960"}
@article{bb387898,
AUTHOR = "Mohanty, M.N. and Jena, B.",
TITLE = "Analysis of stressed human speech",
JOURNAL = IJCVR,
VOLUME = "2",
YEAR = "2011",
NUMBER = "2",
PAGES = "180-187",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381961"}
@article{bb387899,
AUTHOR = "Lopez Moreno, I. and Ramos, D. and Gonzalez Dominguez, J. and Gonzalez Rodriguez, J.",
TITLE = "Von Mises-Fisher Models in the Total Variability Subspace for Language
Recognition",
JOURNAL = SPLetters,
VOLUME = "18",
YEAR = "2011",
NUMBER = "12",
MONTH = "December",
PAGES = "705-708",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT381962"}
Last update:Sep 30, 2026 at 11:45:00