@article{bb369900,
AUTHOR = "Schroder, M. and Bevacqua, E. and Cowie, R. and Eyben, F. and Gunes, H. and Heylen, D. and ter Maat, M. and McKeown, G. and Pammi, S. and Pantic, M. and Pelachaud, C. and Schuller, B. and de Sevin, E. and Valstar, M.F. and Wollmer, M.",
TITLE = "Building Autonomous Sensitive Artificial Listeners",
JOURNAL = AffCom,
VOLUME = "3",
YEAR = "2012",
NUMBER = "2",
PAGES = "165-183",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364052"}
@article{bb369901,
AUTHOR = "Furui, S. and Deng, L. and Gales, M. and Ney, H. and Tokuda, K.",
TITLE = "Fundamental Technologies in Modern Speech Recognition",
JOURNAL = SPMag,
VOLUME = "29",
YEAR = "2012",
NUMBER = "3",
PAGES = "16-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364053"}
@article{bb369902,
AUTHOR = "Saon, G. and Chien, J.T.",
TITLE = "Large-Vocabulary Continuous Speech Recognition Systems:
A Look at Some Recent Advances",
JOURNAL = SPMag,
VOLUME = "29",
YEAR = "2012",
NUMBER = "3",
PAGES = "18-33",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364054"}
@article{bb369903,
AUTHOR = "Wang, H.P. and Leung, C.C. and Lee, T. and Ma, B. and Li, H.Z.",
TITLE = "Shifted-Delta MLP Features for Spoken Language Recognition",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "1",
MONTH = "January",
PAGES = "15-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364055"}
@article{bb369904,
AUTHOR = "Edwards, J.",
TITLE = "Researchers Push Speech Recognition Toward the Mainstream",
JOURNAL = SPMag,
VOLUME = "30",
YEAR = "2012",
NUMBER = "1",
PAGES = "8-11",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364056"}
@article{bb369905,
AUTHOR = "Das, B. and Mandal, S. and Mitra, P. and Basu, A.",
TITLE = "Aging speech recognition with speaker adaptation techniques:
Study on medium vocabulary continuous Bengali speech",
JOURNAL = PRL,
VOLUME = "34",
YEAR = "2013",
NUMBER = "3",
MONTH = "February",
PAGES = "335-343",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364057"}
@article{bb369906,
AUTHOR = "Keefer, R. and Liu, Y. and Bourbakis, N.",
TITLE = "The Development and Evaluation of an Eyes-Free Interaction Model for
Mobile Reading Devices",
JOURNAL = HMS,
VOLUME = "43",
YEAR = "2013",
NUMBER = "1",
MONTH = "January",
PAGES = "76-91",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364058"}
@article{bb369907,
AUTHOR = "O'Shaughnessy, D. and Deng, L. and Li, H.",
TITLE = "Speech Information Processing: Theory and Applications",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1034-1037",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364059"}
@article{bb369908,
AUTHOR = "O'Shaughnessy, D.",
TITLE = "Acoustic Analysis for Automatic Speech Recognition",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1038-1053",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364060"}
@article{bb369909,
AUTHOR = "Fosler Lussier, E. and He, Y. and Jyothi, P. and Prabhavalkar, R.",
TITLE = "Conditional Random Fields in Speech, Audio, and Language Processing",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1054-1075",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364061"}
@article{bb369910,
AUTHOR = "Hermansky, H.",
TITLE = "Multistream Recognition of Speech: Dealing With Unknown Unknowns",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1076-1088",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364062"}
@article{bb369911,
AUTHOR = "Lee, C.H. and Siniscalchi, S.M.",
TITLE = "An Information-Extraction Approach to Speech Processing: Analysis,
Detection, Verification, and Recognition",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1089-1115",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364063"}
@article{bb369912,
AUTHOR = "He, X. and Deng, L.",
TITLE = "Speech-Centric Information Processing: An Optimization-Oriented
Approach",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1116-1135",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364064"}
@article{bb369913,
AUTHOR = "Young, S. and Gasic, M. and Thomson, B. and Williams, J.D.",
TITLE = "POMDP-Based Statistical Spoken Dialog Systems: A Review",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1160-1179",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364065"}
@article{bb369914,
AUTHOR = "Li, W.F. and Zhou, Y.C. and Poh, N. and Zhou, F. and Liao, Q.M.",
TITLE = "Feature Denoising Using Joint Sparse Representation for
In-Car Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "7",
PAGES = "681-684",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364066"}
@article{bb369915,
AUTHOR = "Hermansky, H. and Cohen, J.R. and Stern, R.M.",
TITLE = "Perceptual Properties of Current Speech Recognition Technology",
JOURNAL = PIEEE,
VOLUME = "101",
YEAR = "2013",
NUMBER = "9",
PAGES = "1968-1985",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364067"}
@article{bb369916,
AUTHOR = "Kolossa, D. and Zeiler, S. and Saeidi, R. and Astudillo, R.F.",
TITLE = "Noise-Adaptive LDA: A New Approach for Speech Recognition Under
Observation Uncertainty",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "11",
PAGES = "1018-1021",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364068"}
@article{bb369917,
AUTHOR = "Saeidi, R. and Astudillo, R.F. and Kolossa, D.",
TITLE = "Uncertain LDA: Including Observation Uncertainties in Discriminative
Transforms",
JOURNAL = PAMI,
VOLUME = "38",
YEAR = "2016",
NUMBER = "7",
MONTH = "July",
PAGES = "1479-1488",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364069"}
@article{bb369918,
AUTHOR = "Kim, K.T. and Lin, K.H. and Walther, D.B. and Hasegawa Johnson, M.A. and Huang, T.S.",
TITLE = "Automatic detection of auditory salience with optimized linear
filters derived from human annotation",
JOURNAL = PRL,
VOLUME = "38",
YEAR = "2014",
NUMBER = "1",
PAGES = "78-85",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364070"}
@article{bb369919,
AUTHOR = "Huang, X.D. and Baker, J. and Reddy, R.",
TITLE = "A Historical Perspective of Speech Recognition",
JOURNAL = CACM,
VOLUME = "57",
YEAR = "2014",
NUMBER = "1",
MONTH = "January",
PAGES = "94-103",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364071"}
@article{bb369920,
AUTHOR = "Shi, Y.Z. and Zhang, W.Q. and Cai, M. and Liu, J.",
TITLE = "Efficient One-Pass Decoding with NNLM for Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "21",
YEAR = "2014",
NUMBER = "4",
MONTH = "April",
PAGES = "377-381",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364072"}
@article{bb369921,
AUTHOR = "Zhang, W.B. and Fung, P.",
TITLE = "Efficient Sparse Banded Acoustic Models for Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "21",
YEAR = "2014",
NUMBER = "3",
MONTH = "March",
PAGES = "280-283",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364073"}
@article{bb369922,
AUTHOR = "Triefenbach, F. and Demuynck, K. and Martens, J.P.",
TITLE = "Large Vocabulary Continuous Speech Recognition With Reservoir-Based
Acoustic Models",
JOURNAL = SPLetters,
VOLUME = "21",
YEAR = "2014",
NUMBER = "3",
MONTH = "March",
PAGES = "311-315",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364074"}
@article{bb369923,
AUTHOR = "Diez, M. and Varona, A. and Penagarikano, M. and Rodriguez Fuentes, L.J. and Bordel, G.",
TITLE = "On the Complementarity of Phone Posterior Probabilities for Improved
Speaker Recognition",
JOURNAL = SPLetters,
VOLUME = "21",
YEAR = "2014",
NUMBER = "6",
MONTH = "June",
PAGES = "649-652",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364075"}
@inproceedings{bb369924,
AUTHOR = "Diez, M. and Penagarikano, M. and Varona, A. and Rodriguez Fuentes, L.J. and Bordel, G.",
TITLE = "On the Use of Dot Scoring for Speaker Diarization",
BOOKTITLE = IbPRIA11,
YEAR = "2011",
PAGES = "612-619",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364076"}
@article{bb369925,
AUTHOR = "Rasanen, O. and Laine, U.K.",
TITLE = "A method for noise-robust context-aware pattern discovery and
recognition from categorical sequences",
JOURNAL = PR,
VOLUME = "45",
YEAR = "2012",
NUMBER = "1",
PAGES = "606-616",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364077"}
@article{bb369926,
AUTHOR = "Liu, N.H.",
TITLE = "Effective Results Ranking for Mobile Query by Singing/Humming Using a
Hybrid Recommendation Mechanism",
JOURNAL = MultMed,
VOLUME = "16",
YEAR = "2014",
NUMBER = "5",
MONTH = "August",
PAGES = "1407-1420",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364078"}
@article{bb369927,
AUTHOR = "Schneiderman, R.",
TITLE = "Accuracy, Apps Advance Speech Recognition",
JOURNAL = SPMag,
VOLUME = "32",
YEAR = "2015",
NUMBER = "1",
MONTH = "January",
PAGES = "12-125",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364079"}
@article{bb369928,
AUTHOR = "Ban, S.M. and Kim, H.S.",
TITLE = "Weight-Space Viterbi Decoding Based Spectral Subtraction for
Reverberant Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "9",
MONTH = "September",
PAGES = "1424-1428",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364080"}
@article{bb369929,
AUTHOR = "Sakano, T. and Kobayashi, Y. and Kondo, K.",
TITLE = "A Speech Intelligibility Estimation Method Using a Non-reference
Feature Set",
JOURNAL = IEICE,
VOLUME = "E98-D",
YEAR = "2015",
NUMBER = "1",
MONTH = "January",
PAGES = "21-28",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364081"}
@article{bb369930,
AUTHOR = "Khaldi, K. and Boudraa, A.O. and Torresani, B. and Chonavel, T.",
TITLE = "HHT-based audio coding",
JOURNAL = SIViP,
VOLUME = "9",
YEAR = "2015",
NUMBER = "1",
MONTH = "January",
PAGES = "107-115",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364082"}
@article{bb369931,
AUTHOR = "Savchenko, A.V. and Savchenko, L.V.",
TITLE = "Towards the creation of reliable voice control system based on a
fuzzy approach",
JOURNAL = PRL,
VOLUME = "65",
YEAR = "2015",
NUMBER = "1",
PAGES = "145-151",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364083"}
@article{bb369932,
AUTHOR = "Suh, Y.J. and Kim, H.",
TITLE = "Probabilistic Class Histogram Equalization Based on Posterior Mean
Estimation for Robust Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "12",
MONTH = "December",
PAGES = "2421-2424",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364084"}
@article{bb369933,
AUTHOR = "Wang, X.Y. and Yamamoto, S.",
TITLE = "Speech Recognition of English by Japanese Using Lexicon
Represented by Multiple Reduced Phoneme Sets",
JOURNAL = IEICE,
VOLUME = "E98-D",
YEAR = "2015",
NUMBER = "12",
MONTH = "December",
PAGES = "2271-2279",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364085"}
@article{bb369934,
AUTHOR = "Tohidypour, H.R. and Banitalebi Dehkordi, A.",
TITLE = "Speech frame recognition based on less shift sensitive wavelet filter
banks",
JOURNAL = SIViP,
VOLUME = "10",
YEAR = "2016",
NUMBER = "4",
MONTH = "April",
PAGES = "633-637",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364086"}
@article{bb369935,
AUTHOR = "Ansari, J.A. and Sathyamurthy, A. and Balasubramanyam, R.",
TITLE = "An Open Voice Command Interface Kit",
JOURNAL = HMS,
VOLUME = "46",
YEAR = "2016",
NUMBER = "3",
MONTH = "June",
PAGES = "467-473",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364087"}
@article{bb369936,
AUTHOR = "Cho, B.J. and Kwon, H. and Cho, J.W. and Kim, C. and Stern, R.M. and Park, H.M.",
TITLE = "A Subband-Based Stationary-Component Suppression Method Using
Harmonics and Power Ratio for Reverberant Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "6",
MONTH = "June",
PAGES = "780-784",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364088"}
@article{bb369937,
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#TT364089"}
@article{bb369938,
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#TT364090"}
@article{bb369939,
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#TT364091"}
@article{bb369940,
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#TT364092"}
@article{bb369941,
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#TT364093"}
@article{bb369942,
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#TT364094"}
@article{bb369943,
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#TT364095"}
@article{bb369944,
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#TT364096"}
@article{bb369945,
AUTHOR = "Yang, B.H. and Yao, Z.P. and Lu, H. and Zhou, Y.Q. and Xu, J.K.",
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#TT364097"}
@article{bb369946,
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#TT364098"}
@article{bb369947,
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#TT364099"}
@article{bb369948,
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#TT364100"}
@article{bb369949,
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#TT364101"}
@article{bb369950,
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#TT364102"}
@article{bb369951,
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#TT364103"}
@inproceedings{bb369952,
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#TT364104"}
@article{bb369953,
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#TT364105"}
@article{bb369954,
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#TT364106"}
@article{bb369955,
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#TT364107"}
@article{bb369956,
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#TT364108"}
@article{bb369957,
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#TT364109"}
@article{bb369958,
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#TT364110"}
@article{bb369959,
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#TT364111"}
@article{bb369960,
AUTHOR = "Lu, L. and Kanda, N. and Li, J.Y. 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#TT364112"}
@article{bb369961,
AUTHOR = "Yi, C. and Zhou, S.Y. 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#TT364113"}
@article{bb369962,
AUTHOR = "Xu, P. and Huang, Y. and Yuan, T. and Xiang, T. and Hospedales, T.M. and Song, Y.Z. and Wang, L.",
TITLE = "On Learning Semantic Representations for Large-Scale Abstract
Sketches",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "9",
MONTH = "September",
PAGES = "3366-3379",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364114"}
@article{bb369963,
AUTHOR = "Kim, J. and Lee, Y.",
TITLE = "Improving End-to-End Contextual Speech Recognition via a
Word-Matching Algorithm With Backward Search",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "2087-2091",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364115"}
@article{bb369964,
AUTHOR = "Zhu, S. and Zhang, Y. and He, K. and Zhao, L.",
TITLE = "Acoustic Word Embedding Based on Multi-Head Attention Quadruplet
Network",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "184-188",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364116"}
@article{bb369965,
AUTHOR = "Tiwari, R. and Sharma, V. and Sahoo, R.C.",
TITLE = "Isolated spoken word recognition using packed-MFCC on padded-voice
signal for unscripted languages",
JOURNAL = IJCVR,
VOLUME = "12",
YEAR = "2022",
NUMBER = "2",
PAGES = "120-140",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364117"}
@article{bb369966,
AUTHOR = "Tian, Z.K. and Yi, J.Y. and Tao, J.H. and Zhang, S. and Wen, Z.Q.",
TITLE = "Hybrid Autoregressive and Non-Autoregressive Transformer Models for
Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "762-766",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364118"}
@article{bb369967,
AUTHOR = "Xiao, F.Y. and Guan, J. and Lan, H.Y. and Zhu, Q. and Wang, W.W.",
TITLE = "Local Information Assisted Attention-Free Decoder for Audio
Captioning",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1604-1608",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364119"}
@article{bb369968,
AUTHOR = "Perochon, S.",
TITLE = "A Presentation and Short Discussion of rVAD-fast, a Fast Voice
Activity Detector",
JOURNAL = IPOL,
VOLUME = "12",
YEAR = "2022",
PAGES = "404-419",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364120"}
@article{bb369969,
AUTHOR = "Huang, H.J. and Huang, P.J. and Zhu, Z.B. and Li, J. and Lin, P.",
TITLE = "CLID: A Chunk-Level Intent Detection Framework for Multiple Intent
Spoken Language Understanding",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2123-2127",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364121"}
@article{bb369970,
AUTHOR = "Du, X. and Pun, C.M.",
TITLE = "Robust Audio Patch Attacks Using Physical Sample Simulation and
Adversarial Patch Noise Generation",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "4381-4393",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364122"}
@article{bb369971,
AUTHOR = "Kim, H. and Park, J. and Lee, J.W.",
TITLE = "Generating Transferable Adversarial Examples for Speech
Classification",
JOURNAL = PR,
VOLUME = "137",
YEAR = "2023",
PAGES = "109286",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364123"}
@article{bb369972,
AUTHOR = "Wei, G.Y. and Duan, Z.K. and Li, S. and Yu, X.M. and Yang, G.G.",
TITLE = "LFEformer: Local Feature Enhancement Using Sliding Window With
Deformability for Automatic Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "180-184",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364124"}
@article{bb369973,
AUTHOR = "Xiao, F.Y. and Guan, J. and Zhu, Q. and Wang, W.W.",
TITLE = "Graph Attention for Automated Audio Captioning",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "413-417",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364125"}
@article{bb369974,
AUTHOR = "Chang, C.M. and Lee, C.C.",
TITLE = "Learning Enhanced Acoustic Latent Representation for Small Scale
Affective Corpus with Adversarial Cross Corpora Integration",
JOURNAL = AffCom,
VOLUME = "14",
YEAR = "2023",
NUMBER = "2",
MONTH = "April",
PAGES = "1308-1321",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364126"}
@article{bb369975,
AUTHOR = "Qu, H.L. and Su, X.D. and Wang, Y. and Hao, X. and Gao, G.L.",
TITLE = "Noise-Separated Adaptive Feature Distillation for Robust Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "763-767",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364127"}
@article{bb369976,
AUTHOR = "Nga, C.H. and Vu, D.Q. and Luong, H.H. and Huang, C.L. and Wang, J.C.",
TITLE = "Cyclic Transfer Learning for Mandarin-English Code-Switching Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1387-1391",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364128"}
@article{bb369977,
AUTHOR = "Dong, F. and Qian, Y.Y. and Wang, T.L. and Liu, P. and Cao, J.W.",
TITLE = "A Transformer-Based End-to-End Automatic Speech Recognition Algorithm",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1592-1596",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364129"}
@article{bb369978,
AUTHOR = "Fan, P. and Shan, C.H. and Sun, S.N. and Yang, Q. and Zhang, J.W.",
TITLE = "Key Frame Mechanism for Efficient Conformer Based End-to-End Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1612-1616",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364130"}
@article{bb369979,
AUTHOR = "Mahmoudi, H. and Camboim, S. and Brovelli, M.A.",
TITLE = "Development of a Voice Virtual Assistant for the Geospatial Data
Visualization Application on the Web",
JOURNAL = IJGI,
VOLUME = "12",
YEAR = "2023",
NUMBER = "11",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364131"}
@article{bb369980,
AUTHOR = "Vitolo, P. and Liguori, R. and di Benedetto, L. and Rubino, A. and Licciardo, G.D.",
TITLE = "Automatic Audio Feature Extraction for Keyword Spotting",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "161-165",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364132"}
@article{bb369981,
AUTHOR = "Li, J.H. and Duan, Z.K. and Li, S. and Yu, X.M. and Yang, G.G.",
TITLE = "ESAformer: Enhanced Self-Attention for Automatic Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "471-475",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364133"}
@article{bb369982,
AUTHOR = "Nie, W.Z. and Bao, Y. and Zhao, Y. and Liu, A.",
TITLE = "Long Dialogue Emotion Detection Based on Commonsense Knowledge Graph
Guidance",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "514-528",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364134"}
@article{bb369983,
AUTHOR = "Sun, T.L. and Chen, H.N. and Hu, G.S. and He, L.H. and Zhao, C.R.",
TITLE = "Explainability of Speech Recognition Transformers via Gradient-Based
Attention Visualization",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1395-1406",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364135"}
@article{bb369984,
AUTHOR = "Jacobs, C. and Kamper, H.",
TITLE = "Leveraging Multilingual Transfer for Unsupervised Semantic Acoustic
Word Embeddings",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "311-315",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364136"}
@article{bb369985,
AUTHOR = "Wang, F.Y. and Xu, B. and Xu, B.",
TITLE = "SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR
Using Sequentially Sampled Chunks and Chunked Causal Convolution",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "421-425",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364137"}
@article{bb369986,
AUTHOR = "Fan, R. and Shankar, N.B. and Alwan, A.",
TITLE = "UniEnc-CASSNAT: An Encoder-Only Non-Autoregressive ASR for Speech SSL
Models",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "711-715",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364138"}
@article{bb369987,
AUTHOR = "Xing, B. and Tsang, I.W.",
TITLE = "Co-Guiding for Multi-Intent Spoken Language Understanding",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "2965-2980",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364139"}
@article{bb369988,
AUTHOR = "Hwang, K. and Jung, I.H. and Lee, J.M.",
TITLE = "An implementation of searchable video player",
JOURNAL = IJCVR,
VOLUME = "14",
YEAR = "2024",
NUMBER = "3",
PAGES = "325-337",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364140"}
@article{bb369989,
AUTHOR = "Ma, Y.K. and Zhang, C. and Chen, Q. and Wang, W. and Ma, B.",
TITLE = "Tuning Large Language Model for Speech Recognition With Mixed-Scale
Re-Tokenization",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1740-1744",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364141"}
@article{bb369990,
AUTHOR = "Mu, B.S. and Wan, X. and Zheng, N. and Zhou, H. and Xie, L.",
TITLE = "MMGER: Multi-Modal and Multi-Granularity Generative Error Correction
With LLM for Joint Accent and Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1940-1944",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364142"}
@article{bb369991,
AUTHOR = "Shi, Y. and Li, L. and Wang, D. and Han, J.Q.",
TITLE = "Keyword Guided Target Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1945-1949",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364143"}
@article{bb369992,
AUTHOR = "Gao, X.X. and Li, Z.X. and Chen, Y.M. and Liu, C. and Li, H.Z.",
TITLE = "Transferable Adversarial Attacks Against ASR",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2200-2204",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364144"}
@article{bb369993,
AUTHOR = "Lu, H. and Cheng, G.F. and Yan, Y.H.",
TITLE = "Conversational Short-Phrase Speaker Diarization via Self-Adjusting
Speech Segmentation and Embedding Extraction",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2340-2344",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364145"}
@article{bb369994,
AUTHOR = "Lee, C.W. and Lee, J.H. and Chang, J.H.",
TITLE = "Language Model Personalization for Speech Recognition: A Clustered
Federated Learning Approach With Adaptive Weight Average",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2710-2714",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364146"}
@article{bb369995,
AUTHOR = "Xing, B. and Tsang, I.W.",
TITLE = "HC2L: Hybrid and Cooperative Contrastive Learning for Cross-Lingual
Spoken Language Understanding",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "8094-8105",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364147"}
@article{bb369996,
AUTHOR = "Chang, X. and Guo, P.C. and Fujita, Y. and Maekaku, T. and Watanabe, S.",
TITLE = "MC-Whisper: Extending Speech Foundation Models to Multichannel
Distant Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2850-2854",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364148"}
@article{bb369997,
AUTHOR = "Chen, Y.Q. and Niu, T. and Zhang, H. and Zhang, W. and Qu, D.",
TITLE = "Meta-Prompt: Boosting Whisper's Performance in Low-Resource Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "3039-3043",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364149"}
@article{bb369998,
AUTHOR = "Zheng, L. and Zhu, H. and Tian, S. and Zhao, Q.W. and Li, T.",
TITLE = "Unsupervised Domain Adaptation on End-to-End Multi-Talker Overlapped
Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "3119-3123",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364150"}
@article{bb369999,
AUTHOR = "Lee, H. and Yoon, J.W. and Kim, S.S. and Kim, N.S.",
TITLE = "Towards Maximum Likelihood Training for Transducer-Based Streaming
Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "26-30",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1023.html#TT364151"}
Last update:Nov 26, 2025 at 20:24:09