@article{bb368800,
AUTHOR = "Ozawa, K. and Tsukahara, S. and Kinoshita, Y. and Morise, M.",
TITLE = "Development of an Estimation Model for Instantaneous Presence in
Audio-Visual Content",
JOURNAL = IEICE,
VOLUME = "E99-D",
YEAR = "2016",
NUMBER = "1",
MONTH = "January",
PAGES = "120-127",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362958"}
@article{bb368801,
AUTHOR = "Yao, X. and Jitsuhiro, T. and Miyajima, C. and Kitaoka, N. and Takeda, K.",
TITLE = "Modeling of Physical Characteristics of Speech under Stress",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "10",
MONTH = "October",
PAGES = "1801-1805",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362959"}
@article{bb368802,
AUTHOR = "Adiga, N. and Prasanna, S.R.M.",
TITLE = "Detection of Glottal Activity Using Different Attributes of Source
Information",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "11",
MONTH = "November",
PAGES = "2107-2111",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362960"}
@article{bb368803,
AUTHOR = "Tong, R.J. and Ye, Z.F.",
TITLE = "Supplementations to the Higher Order Subspace Algorithm for
Suppression of Spatially Colored Noise",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "5",
MONTH = "May",
PAGES = "668-672",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362961"}
@article{bb368804,
AUTHOR = "Meenakshi, G.N. and Ghosh, P.K.",
TITLE = "Robust Whisper Activity Detection Using Long-Term Log Energy
Variation of Sub-Band Signal",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "11",
MONTH = "November",
PAGES = "1859-1863",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362962"}
@article{bb368805,
AUTHOR = "Hsu, C.C. and Cheong, K.M. and Chi, T.S. and Tsao, Y.",
TITLE = "Robust Voice Activity Detection Algorithm Based on Feature of Frequency
Modulation of Harmonics and Its DSP Implementation",
JOURNAL = IEICE,
VOLUME = "E98-D",
YEAR = "2015",
NUMBER = "10",
MONTH = "October",
PAGES = "1808-1817",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362963"}
@article{bb368806,
AUTHOR = "Lachachi, N.E. and Adla, A.",
TITLE = "Two approaches-based L2-SVMs reduced to MEB problems for dialect
identification",
JOURNAL = IJCVR,
VOLUME = "6",
YEAR = "2016",
NUMBER = "1-2",
PAGES = "1-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362964"}
@article{bb368807,
AUTHOR = "Braun, S. and Habets, E.A.P.",
TITLE = "Online Dereverberation for Dynamic Scenarios Using a Kalman Filter
With an Autoregressive Model",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "12",
MONTH = "December",
PAGES = "1741-1745",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362965"}
@article{bb368808,
AUTHOR = "Chakrabarty, S. and Habets, E.A.P.",
TITLE = "On the Numerical Instability of an LCMV Beamformer for a Uniform
Linear Array",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "2",
MONTH = "February",
PAGES = "272-276",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362966"}
@article{bb368809,
AUTHOR = "Cherkassky, D. and Gannot, S.",
TITLE = "New Insights into the Kalman Filter Beamformer:
Applications to Speech and Robustness",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "3",
MONTH = "March",
PAGES = "376-380",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362967"}
@article{bb368810,
AUTHOR = "Helmrich, C.R. and Edler, B.",
TITLE = "Audio Coding Using Overlap and Kernel Adaptation",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "5",
MONTH = "May",
PAGES = "590-594",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362968"}
@article{bb368811,
AUTHOR = "Eyben, F. and Scherer, K.R. and Schuller, B.W. and Sundberg, J. and Andre, E. and Busso, C. and Devillers, L.Y. and Epps, J. and Laukka, P. and Narayanan, S.S. and Truong, K.P.",
TITLE = "The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice
Research and Affective Computing",
JOURNAL = AffCom,
VOLUME = "7",
YEAR = "2016",
NUMBER = "2",
MONTH = "April",
PAGES = "190-202",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362969"}
@article{bb368812,
AUTHOR = "Wang, J. and Shang, Y. and Jiang, S. and Gowda, D. and Lv, K.",
TITLE = "Whispered Speech Detection Using Fusion of Group-Delay-Based Subband
Modulation Spectrum and Correntropy Features",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "8",
MONTH = "August",
PAGES = "1042-1046",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362970"}
@article{bb368813,
AUTHOR = "Lopez Oller, D. and Gomez, A.M. and Perez Cordoba, J.L. and Sanchez, V.",
TITLE = "An Error Mitigation Technique for Erasure Channels Based on a Wavelet
Representation of the Speech Excitation Signal",
JOURNAL = MultMed,
VOLUME = "18",
YEAR = "2016",
NUMBER = "7",
MONTH = "July",
PAGES = "1245-1256",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362971"}
@article{bb368814,
AUTHOR = "Strasser, F. and Puder, H.",
TITLE = "Correlation Detection for Adaptive Feedback Cancellation in Hearing
Aids",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "7",
MONTH = "July",
PAGES = "979-983",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362972"}
@article{bb368815,
AUTHOR = "Park, J. and Jin, Y.G. and Hwang, S. and Shin, J.W.",
TITLE = "Dual Microphone Voice Activity Detection Exploiting Interchannel Time
and Level Differences",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "10",
MONTH = "October",
PAGES = "1335-1339",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362973"}
@article{bb368816,
AUTHOR = "Kobayashi, K. and Toda, T. and Nakano, T. and Goto, M. and Nakamura, S.",
TITLE = "Improvements of Voice Timbre Control Based on Perceived Age in Singing
Voice Conversion",
JOURNAL = IEICE,
VOLUME = "E99-D",
YEAR = "2016",
NUMBER = "11",
MONTH = "November",
PAGES = "2767-2777",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362974"}
@article{bb368817,
AUTHOR = "Wang, Y. and Zhao, S. and Li, J. and Kuang, J.",
TITLE = "Speech Bandwidth Extension Using Recurrent Temporal Restricted
Boltzmann Machines",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "12",
MONTH = "December",
PAGES = "1877-1881",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362975"}
@article{bb368818,
AUTHOR = "Prathosh, A.P. and Sujith, P. and Ramakrishnan, A.G. and Kumar Ghosh, P.",
TITLE = "Cumulative Impulse Strength for Epoch Extraction",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "4",
MONTH = "April",
PAGES = "424-428",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362976"}
@article{bb368819,
AUTHOR = "Vignolo, L.D. and Prasanna, S.R.M. and Dandapat, S. and Rufiner, H.L. and Milone, D.H.",
TITLE = "Feature optimisation for stress recognition in speech",
JOURNAL = PRL,
VOLUME = "84",
YEAR = "2016",
NUMBER = "1",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362977"}
@article{bb368820,
AUTHOR = "Jukic, A. and van Waterschoot, T. and Doclo, S.",
TITLE = "Adaptive Speech Dereverberation Using Constrained Sparse Multichannel
Linear Prediction",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "1",
MONTH = "January",
PAGES = "101-105",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362978"}
@article{bb368821,
AUTHOR = "Jiao, Y. and Berisha, V. and Liss, J. and Hsu, S.C. and Levy, E. and McAuliffe, M.",
TITLE = "Articulation Entropy: An Unsupervised Measure of Articulatory
Precision",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "4",
MONTH = "April",
PAGES = "485-489",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362979"}
@article{bb368822,
AUTHOR = "Airaksinen, M. and Bollepalli, B. and Pohjalainen, J. and Alku, P.",
TITLE = "Glottal Vocoding With Frequency-Warped Time-Weighted Linear
Prediction",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "4",
MONTH = "April",
PAGES = "446-450",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362980"}
@article{bb368823,
AUTHOR = "Chetupalli, S.R. and Sreenivas, T.V.",
TITLE = "Joint Bayesian Estimation of Time-Varying LP Parameters and
Excitation for Speech",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "4",
MONTH = "April",
PAGES = "357-361",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362981"}
@inproceedings{bb368824,
AUTHOR = "Chollet, M. and Scherer, S.",
TITLE = "Assessing Public Speaking Ability from Thin Slices of Behavior",
BOOKTITLE = FG17,
YEAR = "2017",
PAGES = "310-316",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362982"}
@article{bb368825,
AUTHOR = "de la Calle Silos, F. and Stern, R.M.",
TITLE = "Synchrony-Based Feature Extraction for Robust Automatic Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "8",
MONTH = "August",
PAGES = "1158-1162",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362983"}
@article{bb368826,
AUTHOR = "Zhang, Q. and Chen, Z. and Yin, F.",
TITLE = "Speaker Tracking Based on Distributed Particle Filter in Distributed
Microphone Networks",
JOURNAL = SMCS,
VOLUME = "47",
YEAR = "2017",
NUMBER = "9",
MONTH = "September",
PAGES = "2433-2443",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362984"}
@article{bb368827,
AUTHOR = "Avila, F.R. and Tcheou, M.P. and Biscainho, L.W.P.",
TITLE = "Audio Soft Declipping Based on Constrained Weighted Least Squares",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "9",
MONTH = "September",
PAGES = "1348-1352",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362985"}
@article{bb368828,
AUTHOR = "Huang, Z. and Siniscalchi, S.M. and Lee, C.H.",
TITLE = "Hierarchical Bayesian combination of plug-in maximum a posteriori
decoders in deep neural networks-based speech recognition and speaker
adaptation",
JOURNAL = PRL,
VOLUME = "98",
YEAR = "2017",
NUMBER = "1",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362986"}
@article{bb368829,
AUTHOR = "Nishimura, R. and Enomoto, S. and Kato, H.",
TITLE = "Speech Privacy for Sound Surveillance Using Super-Resolution Based on
Maximum Likelihood and Bayesian Linear Regression",
JOURNAL = IEICE,
VOLUME = "E101-D",
YEAR = "2018",
NUMBER = "1",
MONTH = "January",
PAGES = "53-63",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362987"}
@article{bb368830,
AUTHOR = "Chee, K.Y. and Jin, Z. and Cai, D. and Li, M. and Yap, W.S. and Lai, Y.L. and Goi, B.M.",
TITLE = "Cancellable speech template via random binary orthogonal matrices
projection hashing",
JOURNAL = PR,
VOLUME = "76",
YEAR = "2018",
NUMBER = "1",
PAGES = "273-287",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362988"}
@article{bb368831,
AUTHOR = "Bernardini, A. and Antonacci, F. and Sarti, A.",
TITLE = "Wave Digital Implementation of Robust First-Order Differential
Microphone Arrays",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "2",
MONTH = "February",
PAGES = "253-257",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362989"}
@article{bb368832,
AUTHOR = "Liu, Q. and Wang, W. and de Campos, T.E. and Jackson, P.J.B. and Hilton, A.",
TITLE = "Multiple Speaker Tracking in Spatial Audio via PHD Filtering and
Depth-Audio Fusion",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "7",
MONTH = "July",
PAGES = "1767-1780",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362990"}
@article{bb368833,
AUTHOR = "Lu, R. and Duan, Z. and Zhang, C.",
TITLE = "Listen and Look: Audio-Visual Matching Assisted Speech Source
Separation",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "9",
MONTH = "September",
PAGES = "1315-1319",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362991"}
@article{bb368834,
AUTHOR = "Wu, K.B. and Zhang, D. and Lu, G.M. and Guo, Z.H.",
TITLE = "Joint learning for voice based disease detection",
JOURNAL = PR,
VOLUME = "87",
YEAR = "2019",
PAGES = "130-139",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362992"}
@article{bb368835,
AUTHOR = "Kumar, R.K. and Birla, L. and Rao, K.S.",
TITLE = "A robust unsupervised pattern discovery and clustering of speech
signals",
JOURNAL = PRL,
VOLUME = "116",
YEAR = "2018",
PAGES = "254-261",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362993"}
@inproceedings{bb368836,
AUTHOR = "Gong, C. and Yi, X.W. and Zhao, X.F.",
TITLE = "Pitch Delay Based Adaptive Steganography for AMR Speech Stream",
BOOKTITLE = IWDW18,
YEAR = "2018",
PAGES = "275-289",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362994"}
@article{bb368837,
AUTHOR = "Skovranek, T. and Despotovic, V. and Peric, Z.",
TITLE = "Optimal Fractional Linear Prediction With Restricted Memory",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "5",
MONTH = "May",
PAGES = "760-764",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362995"}
@article{bb368838,
AUTHOR = "Zhang, J. and Koutrouvelis, A.I. and Heusdens, R. and Hendriks, R.C.",
TITLE = "Distributed Rate-Constrained LCMV Beamforming",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "5",
MONTH = "May",
PAGES = "675-679",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362996"}
@article{bb368839,
AUTHOR = "Keerthana, Y.M. and Reddy, M.K. and Rao, K.S.",
TITLE = "CWT-Based Approach for Epoch Extraction From Telephone Quality Speech",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "8",
MONTH = "August",
PAGES = "1107-1111",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362997"}
@article{bb368840,
AUTHOR = "Gurugubelli, K. and Vuppala, A.K.",
TITLE = "Stable Implementation of Zero Frequency Filtering of Speech Signals
for Efficient Epoch Extraction",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "9",
MONTH = "September",
PAGES = "1310-1314",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362998"}
@article{bb368841,
AUTHOR = "Deb, S. and Dandapat, S.",
TITLE = "Emotion Classification Using Segmentation of Vowel-Like and
Non-Vowel-Like Regions",
JOURNAL = AffCom,
VOLUME = "10",
YEAR = "2019",
NUMBER = "3",
MONTH = "July",
PAGES = "360-373",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT362999"}
@article{bb368842,
AUTHOR = "Kotropoulos, C.L.",
TITLE = "Source phone identification using sketches of features",
JOURNAL = IET-Bio,
VOLUME = "3",
YEAR = "2014",
NUMBER = "2",
MONTH = "June",
PAGES = "75-83",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363000"}
@article{bb368843,
AUTHOR = "Rajan, V. and Brutti, A. and Cavallaro, A.",
TITLE = "ConflictNET: End-to-End Learning for Speech-Based Conflict Intensity
Estimation",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "11",
MONTH = "November",
PAGES = "1668-1672",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363001"}
@article{bb368844,
AUTHOR = "Lotfian, R. and Busso, C.",
TITLE = "Building Naturalistic Emotionally Balanced Speech Corpus by
Retrieving Emotional Speech from Existing Podcast Recordings",
JOURNAL = AffCom,
VOLUME = "10",
YEAR = "2019",
NUMBER = "4",
MONTH = "October",
PAGES = "471-483",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363002"}
@article{bb368845,
AUTHOR = "Lee, Y. and Min, J. and Han, D.K. and Ko, H.",
TITLE = "Spectro-Temporal Attention-Based Voice Activity Detection",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "131-135",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363003"}
@article{bb368846,
AUTHOR = "Lim, H. and Kim, Y. and Goo, J. and Kim, H.",
TITLE = "Interlayer Selective Attention Network for Robust Personalized
Wake-Up Word Detection",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "126-130",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363004"}
@article{bb368847,
AUTHOR = "Yang, H. and Yang, Z. and Bao, Y. and Liu, S. and Huang, Y.",
TITLE = "Fast Steganalysis Method for VoIP Streams",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "286-290",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363005"}
@inproceedings{bb368848,
AUTHOR = "Zhang, L.W. and Shi, Z.Q. and Han, J.Q. and Shi, A. and Ma, D.",
TITLE = "Furcanext: End-to-end Monaural Speech Separation with Dynamic Gated
Dilated Temporal Convolutional Networks",
BOOKTITLE = MMMod20,
YEAR = "2020",
PAGES = "I:653-665",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363006"}
@article{bb368849,
AUTHOR = "Lin, X. and Zhu, J. and Chen, D.",
TITLE = "Subband Aware CNN for Cell-Phone Recognition",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "605-609",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363007"}
@article{bb368850,
AUTHOR = "Tagliasacchi, M. and Gfeller, B. and Quitry, F.d.C. and Roblek, D.",
TITLE = "Pre-Training Audio Representations With Self-Supervision",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "600-604",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363008"}
@article{bb368851,
AUTHOR = "Yatabe, K.",
TITLE = "Consistent ICA: Determined BSS Meets Spectrogram Consistency",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "870-874",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363009"}
@article{bb368852,
AUTHOR = "Muralishankar, R. and Ghosh, D. and Gurugopinath, S.",
TITLE = "A Novel Modified Mel-DCT Filter Bank Structure With Application to
Voice Activity Detection",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1240-1244",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363010"}
@article{bb368853,
AUTHOR = "Jiang, F. and Duan, Z.",
TITLE = "Speaker Attractor Network: Generalizing Speech Separation to Unseen
Numbers of Sources",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1859-1863",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363011"}
@article{bb368854,
AUTHOR = "Kim, J. and Lee, Y. and Kim, E.",
TITLE = "Accelerating RNN Transducer Inference via Adaptive Expansion Search",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "2019-2023",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363012"}
@article{bb368855,
AUTHOR = "Janbakhshi, P. and Kodrasi, I. and Bourlard, H.",
TITLE = "Subspace-Based Learning for Automatic Dysarthric Speech Detection",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "96-100",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363013"}
@article{bb368856,
AUTHOR = "Gimeno, P. and Mingote, V. and Ortega, A. and Miguel, A. and Lleida, E.",
TITLE = "Generalizing AUC Optimization to Multiclass Classification for Audio
Segmentation With Limited Training Data",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1135-1139",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363014"}
@article{bb368857,
AUTHOR = "Queiroz, A. and Coelho, R.",
TITLE = "F0-Based Gammatone Filtering for Intelligibility Gain of Acoustic
Noisy Signals",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1225-1229",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363015"}
@article{bb368858,
AUTHOR = "Vrbik, D. and Labus, V.",
TITLE = "Crowdsourcing of Popular Toponyms: How to Collect and Preserve
Toponyms in Spoken Use",
JOURNAL = IJGI,
VOLUME = "10",
YEAR = "2021",
NUMBER = "5",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363016"}
@article{bb368859,
AUTHOR = "Ikeshita, R. and Kinoshita, K. and Kamo, N. and Nakatani, T.",
TITLE = "Online Speech Dereverberation Using Mixture of Multichannel Linear
Prediction Models",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1580-1584",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363017"}
@article{bb368860,
AUTHOR = "Jiang, Y.C. and Leung, F.H.F.",
TITLE = "Vector-Based Feature Representations for Speech Signals:
From Supervector to Latent Vector",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "2641-2655",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363018"}
@article{bb368861,
AUTHOR = "Esmaeilpour, M. and Cardinal, P. and Koerich, A.L.",
TITLE = "Cyclic Defense GAN Against Speech Adversarial Attacks",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1769-1773",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363019"}
@article{bb368862,
AUTHOR = "Kodrasi, I.",
TITLE = "Temporal Envelope and Fine Structure Cues for Dysarthric Speech
Detection Using CNNs",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1853-1857",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363020"}
@article{bb368863,
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/other1024sa1.html#TT363021"}
@article{bb368864,
AUTHOR = "Liu, Z.T. and Rehman, A. and Wu, M. and Cao, W.H. and Hao, M.",
TITLE = "Speech Personality Recognition Based on Annotation Classification
Using Log-Likelihood Distance and Extraction of Essential Audio
Features",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "3414-3426",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363022"}
@article{bb368865,
AUTHOR = "Kim, H.Y. and Yoon, J.W. and Cho, W.I. and Kim, N.S.",
TITLE = "Neurally Optimized Decoder for Low Bitrate Speech Codec",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "244-248",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363023"}
@article{bb368866,
AUTHOR = "Cohen, E. and Kreuk, F. and Keshet, J.",
TITLE = "Speech Time-Scale Modification With GANs",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1067-1071",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363024"}
@article{bb368867,
AUTHOR = "Choi, J. and Chang, J.H.",
TITLE = "Supervised Learning Approach for Explicit Spatial Filtering of Speech",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1412-1416",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363025"}
@article{bb368868,
AUTHOR = "Fu, M.J. and Wang, X.M. and Wang, J.",
TITLE = "Polynomial-Decomposition-Based LPC for Formant Estimation",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1392-1396",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363026"}
@article{bb368869,
AUTHOR = "Kim, M.S. and Kim, H.S.",
TITLE = "Attentive Pooling-Based Weighted Sum of Spectral Decay Rates for
Blind Estimation of Reverberation Time",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1639-1643",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363027"}
@article{bb368870,
AUTHOR = "Reddy, M.K. and Keerthana, Y.M. and Alku, P.",
TITLE = "End-to-End Pathological Speech Detection Using Wavelet Scattering
Network",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1863-1867",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363028"}
@article{bb368871,
AUTHOR = "Karamatli, E. and Kirbiz, S.",
TITLE = "MixCycle: Unsupervised Speech Separation via Cyclic Mixture
Permutation Invariant Training",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2637-2641",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363029"}
@article{bb368872,
AUTHOR = "McKinney, A.F. and Cauchi, B.",
TITLE = "Non-Intrusive Binaural Speech Intelligibility Prediction From
Discrete Latent Representations",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "987-991",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363030"}
@article{bb368873,
AUTHOR = "de Lacerda Pataca, C. and Costa, P.D.P.",
TITLE = "Hidden Bawls, Whispers, and Yelps:
Can Text Convey the Sound of Speech, Beyond Words?",
JOURNAL = AffCom,
VOLUME = "14",
YEAR = "2023",
NUMBER = "1",
MONTH = "January",
PAGES = "6-16",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363031"}
@article{bb368874,
AUTHOR = "Chen, G. and Li, X.G. and Xiao, S.Y. and Zhang, C.H. and Lu, X.H.",
TITLE = "RACL: A robust adaptive contrastive learning method for
conversational satisfaction prediction",
JOURNAL = PR,
VOLUME = "138",
YEAR = "2023",
PAGES = "109386",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363032"}
@article{bb368875,
AUTHOR = "Cheng, J.M. and Liang, R. and Zhao, L. and Huang, C.W. and Schuller, B.W.",
TITLE = "Speech Denoising and Compensation for Hearing Aids Using an
FTCRN-Based Metric GAN",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "374-378",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363033"}
@article{bb368876,
AUTHOR = "Shu, Y.C. and Luo, H.N. and Zhang, S.L. and Wang, L.B. and Dang, J.W.",
TITLE = "A CIF-Based Speech Segmentation Method for Streaming E2E ASR",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "344-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363034"}
@article{bb368877,
AUTHOR = "Zhou, Y. and Wu, Z.Z. and Zhang, M.Y. and Tian, X.H. and Li, H.Z.",
TITLE = "TTS-Guided Training for Accent Conversion Without Parallel Data",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "533-537",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363035"}
@article{bb368878,
AUTHOR = "Koepke, A.S. and Oncescu, A.M. and Henriques, J.F. and Akata, Z. and Albanie, S.",
TITLE = "Audio Retrieval With Natural Language Queries: A Benchmark Study",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "2675-2685",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363036"}
@article{bb368879,
AUTHOR = "Park, D. and Yu, Y. and Katabi, D. and Kim, H.K.",
TITLE = "Adversarial Continual Learning to Transfer Self-Supervised Speech
Representations for Voice Pathology Detection",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "932-936",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363037"}
@article{bb368880,
AUTHOR = "Kim, H. and Shin, J.W.",
TITLE = "On Training Speech Separation Models With Various Numbers of Speakers",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1202-1206",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363038"}
@article{bb368881,
AUTHOR = "Joglekar, A. and Hansen, J.H.L.",
TITLE = "DeepComboSAD: Spectro-Temporal Correlation Based Speech Activity
Detection for Naturalistic Audio Streams",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1472-1476",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363039"}
@article{bb368882,
AUTHOR = "Cai, Y.Q. and Li, L. and Abel, A. and Zhu, X.Y. and Wang, D.",
TITLE = "Maximum Gaussianality training for deep speaker vector normalization",
JOURNAL = PR,
VOLUME = "145",
YEAR = "2024",
PAGES = "109977",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363040"}
@article{bb368883,
AUTHOR = "Raman, C. and Prabhu, N.R. and Hung, H.",
TITLE = "Perceived Conversation Quality in Spontaneous Interactions",
JOURNAL = AffCom,
VOLUME = "14",
YEAR = "2023",
NUMBER = "4",
MONTH = "October",
PAGES = "2901-2912",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363041"}
@inproceedings{bb368884,
AUTHOR = "Atito, S. and Awais, M. and Alex, T. and Kittler, J.V.",
TITLE = "Group Masked Model Learning for General Audio Representation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2600-2604",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363042"}
@article{bb368885,
AUTHOR = "Lee, H. and Saeed, A.",
TITLE = "Distilled non-semantic speech embeddings with binary neural networks
for low-resource devices",
JOURNAL = PRL,
VOLUME = "177",
YEAR = "2024",
PAGES = "15-19",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363043"}
@article{bb368886,
AUTHOR = "Ye, L.X. and Gao, C.F. and Cheng, G.F. and Luo, L.P. and Zhao, Q.W.",
TITLE = "ASQ: An Ultra-Low Bit Rate ASR-Oriented Speech Quantization Method",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "221-225",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363044"}
@article{bb368887,
AUTHOR = "Li, C.T. and Yang, F. and Yang, J.",
TITLE = "Restoration of Bone-Conducted Speech With U-Net-Like Model and Energy
Distance Loss",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "166-170",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363045"}
@article{bb368888,
AUTHOR = "Rababaah, A.R.",
TITLE = "Intelligent classification model for holy Quran recitation Maqams",
JOURNAL = IJCVR,
VOLUME = "14",
YEAR = "2024",
NUMBER = "2",
PAGES = "170-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363046"}
@article{bb368889,
AUTHOR = "Muraleedharan, K.M. and Kumar, K.T.B. and John, S.I. and Kumar, R.K. .S.I.",
TITLE = "Combined Use of Nonlinear Measures for Analyzing Pathological Voices",
JOURNAL = IJIG,
VOLUME = "24",
YEAR = "2024",
NUMBER = "3",
MONTH = "May",
PAGES = "2450035",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363047"}
@article{bb368890,
AUTHOR = "Wang, Z.Q.",
TITLE = "Mixture to Mixture: Leveraging Close-Talk Mixtures as
Weak-Supervision for Speech Separation",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1715-1719",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363048"}
@article{bb368891,
AUTHOR = "Zhang, C. and Jiang, S.",
TITLE = "Detection of QIM-Based Steganography in VoIP Streams:
A MobileViT-Inspired Model",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1735-1739",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363049"}
@article{bb368892,
AUTHOR = "Wang, Z.C. and Chen, Y.Z. and Wang, X.S. and Xie, L. and Wang, Y.P.",
TITLE = "StreamVoice+: Evolving Into End-to-End Streaming Zero-Shot Voice
Conversion",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "3000-3004",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363050"}
@article{bb368893,
AUTHOR = "Guo, N. and Edler, B.",
TITLE = "Frequency Domain Prediction of Tonal Signals With Time-Varying
Pitches",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "31-35",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363051"}
@article{bb368894,
AUTHOR = "Lopez Espejo, I. and Rosello, E. and Edraki, A. and Harte, N. and Jensen, J.",
TITLE = "Noise-Robust Hearing Aid Voice Control",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "241-245",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363052"}
@article{bb368895,
AUTHOR = "Xie, H. and Khorrami, K. and Rasanen, O. and Virtanen, T.",
TITLE = "Text-Based Audio Retrieval by Learning From Similarities Between
Audio Captions",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "221-225",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363053"}
@article{bb368896,
AUTHOR = "Yuan, C.S. and Chen, Y.F. and Zhou, Z. and Xia, Z.H. and Huang, Y.F.",
TITLE = "Compressed Domain Invariant Adversarial Representation Learning for
Robust Audio Deepfake Detection",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1111-1115",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363054"}
@article{bb368897,
AUTHOR = "Unoki, M. and Li, K. and Chaiwongyen, A. and Nguyen, Q.H. and Zaman, K.",
TITLE = "Deepfake Speech Detection: Approaches from Acoustic Features to Deep
Neural Networks",
JOURNAL = IEICE,
VOLUME = "E108-D",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "300-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363055"}
@article{bb368898,
AUTHOR = "Shin, U.H. and Ku, B.H. and Park, H.M.",
TITLE = "TF-CorrNet: Leveraging Spatial Correlation for Continuous Speech
Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1875-1879",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363056"}
@article{bb368899,
AUTHOR = "Ta, B.T. and Le, N.M. and Binh, H.T.T. and Do, V.H.",
TITLE = "Exploring Non-Matching Multiple References for Speech Quality
Assessment",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1610-1614",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT363057"}
Last update:Nov 2, 2025 at 14:03:07