@article{bb265500,
        AUTHOR = "Ren, H. and Yan, Y.",
        TITLE = "Structural Optimization and Online Evolutionary Learning for Spoken
Dialog Management",
        JOURNAL = SPLetters,
        VOLUME = "23",
        YEAR = "2016",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1013-1017",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260204"}

@article{bb265501,
        AUTHOR = "Khoubrouy, S.A. and Hansen, J.H.L.",
        TITLE = "Microphone Array Processing Strategies for Distant-Based Automatic
Speech Recognition",
        JOURNAL = SPLetters,
        VOLUME = "23",
        YEAR = "2016",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1344-1348",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260205"}

@article{bb265502,
        AUTHOR = "Lamberti, F. and Manuri, F. and Paravati, G. and Piumatti, G. and Sanna, A.",
        TITLE = "Using Semantics to Automatically Generate Speech Interfaces for
Wearable Virtual and Augmented Reality Applications",
        JOURNAL = HMS,
        VOLUME = "47",
        YEAR = "2017",
        NUMBER = "1",
        MONTH = "February",
        PAGES = "152-164",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260206"}

@article{bb265503,
        AUTHOR = "Ganapathy, S.",
        TITLE = "Multivariate Autoregressive Spectrogram Modeling for Noisy Speech
Recognition",
        JOURNAL = SPLetters,
        VOLUME = "24",
        YEAR = "2017",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1373-1377",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260207"}

@article{bb265504,
        AUTHOR = "Shahnawazuddin, S. and Adiga, N. and Kathania, H.K.",
        TITLE = "Effect of Prosody Modification on Children's ASR",
        JOURNAL = SPLetters,
        VOLUME = "24",
        YEAR = "2017",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "1749-1753",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260208"}

@article{bb265505,
        AUTHOR = "Monroe, D.",
        TITLE = "Digital Hearing",
        JOURNAL = CACM,
        VOLUME = "60",
        YEAR = "2017",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "18-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260209"}

@article{bb265506,
        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/other1023.html#TT260210"}

@article{bb265507,
        AUTHOR = "Kim, J. and Hahn, M.",
        TITLE = "Voice Activity Detection Using an Adaptive Context Attention Model",
        JOURNAL = SPLetters,
        VOLUME = "25",
        YEAR = "2018",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1181-1185",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260211"}

@article{bb265508,
        AUTHOR = "Edwards, J.",
        TITLE = "Something to Talk About: Signal Processing in Speech and Audiology
Research: Promising Investigations Explore New Opportunities in Human
Communication",
        JOURNAL = SPMag,
        VOLUME = "35",
        YEAR = "2018",
        NUMBER = "6",
        MONTH = "November",
        PAGES = "8-12",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260212"}

@article{bb265509,
        AUTHOR = "Baltrusaitis, T. and Ahuja, C. and Morency, L.P.",
        TITLE = "Multimodal Machine Learning: A Survey and Taxonomy",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "423-443",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260213"}

@article{bb265510,
        AUTHOR = "Shin, Y. and Yoo, K.M. and Lee, S.",
        TITLE = "Utterance Generation With Variational Auto-Encoder for Slot Filling
in Spoken Language Understanding",
        JOURNAL = SPLetters,
        VOLUME = "26",
        YEAR = "2019",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "505-509",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260214"}

@article{bb265511,
        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/other1023.html#TT260215"}

@article{bb265512,
        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/other1023.html#TT260216"}

@article{bb265513,
        AUTHOR = "Meng, Z. and Han, S. and Tong, Y.",
        TITLE = "Listen to Your Face: Inferring Facial Action Units from Audio Channel",
        JOURNAL = AffCom,
        VOLUME = "10",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "October",
        PAGES = "537-551",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260217"}

@article{bb265514,
        AUTHOR = "Yang, B. and Yao, Z. and Lu, H. and Zhou, Y. and Xu, J.",
        TITLE = "In-classroom learning analytics based on student behavior, topic and
teaching characteristic mining",
        JOURNAL = PRL,
        VOLUME = "129",
        YEAR = "2020",
        PAGES = "224-231",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260218"}

@article{bb265515,
        AUTHOR = "Chandrakala, S. and Jayalakshmi, S.L.",
        TITLE = "Generative Model Driven Representation Learning in a Hybrid Framework
for Environmental Audio Scene and Sound Event Recognition",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "3-14",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260219"}

@article{bb265516,
        AUTHOR = "Yadav, I.C. and Pradhan, G.",
        TITLE = "Significance of Pitch-Based Spectral Normalization for Children's
Speech Recognition",
        JOURNAL = SPLetters,
        VOLUME = "26",
        YEAR = "2019",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "1822-1826",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260220"}

@article{bb265517,
        AUTHOR = "Petridis, S. and Wang, Y.J. and Ma, P.C. and Li, Z.W. and Pantic, M.",
        TITLE = "End-to-end visual speech recognition for small-scale datasets",
        JOURNAL = PRL,
        VOLUME = "131",
        YEAR = "2020",
        PAGES = "421-427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260221"}

@article{bb265518,
        AUTHOR = "Shahnawazuddin, S. and Adiga, N. and Kathania, H.K. and Sai, B.T.",
        TITLE = "Creating speaker independent ASR system through prosody modification
based data augmentation",
        JOURNAL = PRL,
        VOLUME = "131",
        YEAR = "2020",
        PAGES = "213-218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260222"}

@article{bb265519,
        AUTHOR = "Park, T.J. and Han, K.J. and Kumar, M. and Narayanan, S.",
        TITLE = "Auto-Tuning Spectral Clustering for Speaker Diarization Using
Normalized Maximum Eigengap",
        JOURNAL = SPLetters,
        VOLUME = "27",
        YEAR = "2020",
        PAGES = "381-385",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260223"}

@article{bb265520,
        AUTHOR = "Deb, S. and Dandapat, S. and Krajewski, J.",
        TITLE = "Analysis and Classification of Cold Speech Using Variational Mode
Decomposition",
        JOURNAL = AffCom,
        VOLUME = "11",
        YEAR = "2020",
        NUMBER = "2",
        MONTH = "April",
        PAGES = "296-307",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260224"}

@article{bb265521,
        AUTHOR = "Sanchez Junquera, J. and Villasenor Pineda, L. and Montes y Gomez, M. and Rosso, P. and Stamatatos, E.",
        TITLE = "Masking domain-specific information for cross-domain deception
detection",
        JOURNAL = PRL,
        VOLUME = "135",
        YEAR = "2020",
        PAGES = "122-130",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260225"}

@inproceedings{bb265522,
        AUTHOR = "Rill Garcia, R. and Villasenor Pineda, L. and Reyes Meza, V. and Escalante, H.J.",
        TITLE = "From Text to Speech: A Multimodal Cross-Domain Approach for Deception
Detection",
        BOOKTITLE = MIPPSNA18,
        YEAR = "2018",
        PAGES = "164-177",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260226"}

@article{bb265523,
        AUTHOR = "Lim, H. and Kim, Y. and Kim, H.",
        TITLE = "Cross-Informed Domain Adversarial Training for Noise-Robust Wake-Up
Word Detection",
        JOURNAL = SPLetters,
        VOLUME = "27",
        YEAR = "2020",
        PAGES = "1769-1773",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260227"}

@article{bb265524,
        AUTHOR = "Zhao, L. and Zhang, A. and Liu, Y. and Fei, H.",
        TITLE = "Encoding multi-granularity structural information for joint Chinese
word segmentation and POS tagging",
        JOURNAL = PRL,
        VOLUME = "138",
        YEAR = "2020",
        PAGES = "163-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260228"}

@article{bb265525,
        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/other1023.html#TT260229"}

@article{bb265526,
        AUTHOR = "Bang, J. and Han, S. and Lee, J.H.",
        TITLE = "Listening-oriented response generation by exploiting user responses",
        JOURNAL = PRL,
        VOLUME = "140",
        YEAR = "2020",
        PAGES = "230-237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260230"}

@article{bb265527,
        AUTHOR = "Zhou, J.T.Y. and Zhang, H. and Jin, D. and Peng, X.",
        TITLE = "Dual Adversarial Transfer for Sequence Labeling",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "434-446",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260231"}

@article{bb265528,
        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/other1023.html#TT260232"}

@article{bb265529,
        AUTHOR = "Chen, N. and Watanabe, S. and Villalba, J. and Zelasko, P. and Dehak, N.",
        TITLE = "Non-Autoregressive Transformer for Speech Recognition",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "121-125",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260233"}

@article{bb265530,
        AUTHOR = "Haeb Umbach, R. and Heymann, J. and Drude, L. and Watanabe, S. and Delcroix, M. and Nakatani, T.",
        TITLE = "Far-Field Automatic Speech Recognition",
        JOURNAL = PIEEE,
        VOLUME = "109",
        YEAR = "2021",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "124-148",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260234"}

@article{bb265531,
        AUTHOR = "Fritsch, J. and Magimai Doss, M.",
        TITLE = "Utterance Verification-Based Dysarthric Speech Intelligibility
Assessment Using Phonetic Posterior Features",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "224-228",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260235"}

@article{bb265532,
        AUTHOR = "Ikeshita, R. and Kamo, N. and Nakatani, T.",
        TITLE = "Blind Signal Dereverberation Based on Mixture of Weighted Prediction
Error Models",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "399-403",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260236"}

@article{bb265533,
        AUTHOR = "Lu, L. and Kanda, N. and Li, J. and Gong, Y.F.",
        TITLE = "Streaming End-to-End Multi-Talker Speech Recognition",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "803-807",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260237"}

@article{bb265534,
        AUTHOR = "Yi, C. and Zhou, S. and Xu, B.",
        TITLE = "Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for
Low-Resource Speech Recognition",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "788-792",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260238"}

@inproceedings{bb265535,
        AUTHOR = "Zhou, L. 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#TT260239"}

@inproceedings{bb265536,
        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/other1023.html#TT260240"}

@inproceedings{bb265537,
        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#TT260241"}

@inproceedings{bb265538,
        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/other1023.html#TT260242"}

@inproceedings{bb265539,
        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#TT260243"}

@inproceedings{bb265540,
        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#TT260244"}

@inproceedings{bb265541,
        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/other1023.html#TT260245"}

@inproceedings{bb265542,
        AUTHOR = "Joshi, P. and Saharia, C. and Singh, V. and Gautam, D. and Ramakrishnan, G. and Jyothi, P.",
        TITLE = "A Tale of Two Modalities for Video Captioning",
        BOOKTITLE = MMVAMTC19,
        YEAR = "2019",
        PAGES = "3708-3712",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260246"}

@inproceedings{bb265543,
        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#TT260247"}

@inproceedings{bb265544,
        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#TT260248"}

@inproceedings{bb265545,
        AUTHOR = "Naszadi, K. and Oualil, Y. and Klakow, D.",
        TITLE = "Image-Sensitive Language Modeling for Automatic Speech Recognition",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:173-179",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260249"}

@inproceedings{bb265546,
        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#TT260250"}

@inproceedings{bb265547,
        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#TT260251"}

@inproceedings{bb265548,
        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#TT260252"}

@inproceedings{bb265549,
        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/other1023.html#TT260253"}

@inproceedings{bb265550,
        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/other1023.html#TT260254"}

@inproceedings{bb265551,
        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#TT260255"}

@inproceedings{bb265552,
        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#TT260256"}

@inproceedings{bb265553,
        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#TT260257"}

@inproceedings{bb265554,
        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#TT260258"}

@inproceedings{bb265555,
        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#TT260259"}

@inproceedings{bb265556,
        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#TT260260"}

@inproceedings{bb265557,
        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#TT260261"}

@inproceedings{bb265558,
        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/other1023.html#TT260262"}

@inproceedings{bb265559,
        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/other1023.html#TT260263"}

@inproceedings{bb265560,
        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#TT260264"}

@inproceedings{bb265561,
        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#TT260265"}

@inproceedings{bb265562,
        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#TT260266"}

@inproceedings{bb265563,
        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#TT260267"}

@inproceedings{bb265564,
        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#TT260268"}

@inproceedings{bb265565,
        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#TT260269"}

@inproceedings{bb265566,
        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/other1023.html#TT260270"}

@inproceedings{bb265567,
        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#TT260271"}

@inproceedings{bb265568,
        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/other1023.html#TT260272"}

@inproceedings{bb265569,
        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/other1023.html#TT260273"}

@inproceedings{bb265570,
        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/other1023.html#TT260274"}

@inproceedings{bb265571,
        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#TT260275"}

@inproceedings{bb265572,
        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#TT260276"}

@inproceedings{bb265573,
        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#TT260277"}

@inproceedings{bb265574,
        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#TT260278"}

@inproceedings{bb265575,
        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#TT260279"}

@inproceedings{bb265576,
        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#TT260280"}

@inproceedings{bb265577,
        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#TT260281"}

@article{bb265578,
        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#TT260282"}

@inproceedings{bb265579,
        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#TT260283"}

@inproceedings{bb265580,
        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#TT260284"}

@inproceedings{bb265581,
        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#TT260285"}

@inproceedings{bb265582,
        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#TT260286"}

@inproceedings{bb265583,
        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#TT260287"}

@inproceedings{bb265584,
        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#TT260288"}

@inproceedings{bb265585,
        AUTHOR = "Chan, K.Y. and Nordholm, S. 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#TT260289"}

@inproceedings{bb265586,
        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#TT260290"}

@inproceedings{bb265587,
        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#TT260291"}

@inproceedings{bb265588,
        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/other1023.html#TT260292"}

@inproceedings{bb265589,
        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#TT260293"}

@inproceedings{bb265590,
        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#TT260294"}

@article{bb265591,
        AUTHOR = "Im, J.H. and Lee, S.Y.",
        TITLE = "Unified Training of Feature Extractor and HMM Classifier for Speech
Recognition",
        JOURNAL = SPLetters,
        VOLUME = "19",
        YEAR = "2012",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "111-114",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT260295"}

@inproceedings{bb265592,
        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#TT260296"}

@inproceedings{bb265593,
        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/other1023.html#TT260297"}

@inproceedings{bb265594,
        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/other1023.html#TT260298"}

@inproceedings{bb265595,
        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#TT260299"}

@inproceedings{bb265596,
        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/other1023.html#TT260300"}

@inproceedings{bb265597,
        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#TT260301"}

@inproceedings{bb265598,
        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#TT260302"}

@inproceedings{bb265599,
        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#TT260303"}

Last update:May 2, 2021 at 12:04:43