@inproceedings{bb378800,
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#TT372894"}
@article{bb378801,
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#TT372895"}
@article{bb378802,
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#TT372896"}
@article{bb378803,
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#TT372897"}
@article{bb378804,
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#TT372898"}
@article{bb378805,
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#TT372899"}
@article{bb378806,
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#TT372900"}
@article{bb378807,
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#TT372901"}
@article{bb378808,
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#TT372902"}
@article{bb378809,
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#TT372903"}
@article{bb378810,
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#TT372904"}
@article{bb378811,
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#TT372905"}
@inproceedings{bb378812,
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#TT372906"}
@article{bb378813,
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#TT372907"}
@article{bb378814,
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#TT372908"}
@article{bb378815,
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#TT372909"}
@article{bb378816,
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#TT372910"}
@article{bb378817,
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#TT372911"}
@article{bb378818,
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#TT372912"}
@article{bb378819,
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#TT372913"}
@article{bb378820,
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#TT372914"}
@article{bb378821,
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#TT372915"}
@article{bb378822,
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#TT372916"}
@article{bb378823,
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#TT372917"}
@inproceedings{bb378824,
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#TT372918"}
@article{bb378825,
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#TT372919"}
@article{bb378826,
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#TT372920"}
@article{bb378827,
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#TT372921"}
@article{bb378828,
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#TT372922"}
@article{bb378829,
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#TT372923"}
@article{bb378830,
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#TT372924"}
@article{bb378831,
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#TT372925"}
@article{bb378832,
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#TT372926"}
@article{bb378833,
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#TT372927"}
@article{bb378834,
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#TT372928"}
@article{bb378835,
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#TT372929"}
@article{bb378836,
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#TT372930"}
@article{bb378837,
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#TT372931"}
@article{bb378838,
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#TT372932"}
@article{bb378839,
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#TT372933"}
@article{bb378840,
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#TT372934"}
@article{bb378841,
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#TT372935"}
@article{bb378842,
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#TT372936"}
@article{bb378843,
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#TT372937"}
@article{bb378844,
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#TT372938"}
@article{bb378845,
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#TT372939"}
@article{bb378846,
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#TT372940"}
@article{bb378847,
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#TT372941"}
@article{bb378848,
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#TT372942"}
@article{bb378849,
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#TT372943"}
@article{bb378850,
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#TT372944"}
@article{bb378851,
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#TT372945"}
@article{bb378852,
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#TT372946"}
@article{bb378853,
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#TT372947"}
@article{bb378854,
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#TT372948"}
@article{bb378855,
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#TT372949"}
@article{bb378856,
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#TT372950"}
@article{bb378857,
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#TT372951"}
@article{bb378858,
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#TT372952"}
@article{bb378859,
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#TT372953"}
@inproceedings{bb378860,
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#TT372954"}
@article{bb378861,
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#TT372955"}
@article{bb378862,
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#TT372956"}
@article{bb378863,
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#TT372957"}
@article{bb378864,
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#TT372958"}
@article{bb378865,
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#TT372959"}
@article{bb378866,
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#TT372960"}
@article{bb378867,
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#TT372961"}
@article{bb378868,
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#TT372962"}
@article{bb378869,
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#TT372963"}
@article{bb378870,
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#TT372964"}
@article{bb378871,
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#TT372965"}
@article{bb378872,
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#TT372966"}
@article{bb378873,
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#TT372967"}
@article{bb378874,
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#TT372968"}
@article{bb378875,
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#TT372969"}
@article{bb378876,
AUTHOR = "Jin, L.B. and Min, D. and Yu, C. and Shin, J.E. and Kim, E.Y.",
TITLE = "Detecting Hearing Impairment Through Localizing Abnormal Speech
Patterns",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1945-1949",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372970"}
@article{bb378877,
AUTHOR = "Liu, D. and Zhang, T.Q. and Wei, Y. and Yi, C. and Christensen, M.G.",
TITLE = "Speech Conv-Mamba: Selective Structured State Space Model With
Temporal Dilated Convolution for Efficient Speech Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2015-2019",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372971"}
@article{bb378878,
AUTHOR = "Liu, F. and Ai, Y. and Ling, Z.H.",
TITLE = "Token-Prediction-Based Post-Processing for Low-Bitrate Speech Coding",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3235-3239",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372972"}
@article{bb378879,
AUTHOR = "Zhang, Z.X. and Xu, W.X. and Dong, Z. and Wang, K.L. and Wu, Y.M. and Peng, J. and Wang, R. and Huang, D.Y.",
TITLE = "ParaLBench: A Large-Scale Benchmark for Computational Paralinguistics
Over Acoustic Foundation Models",
JOURNAL = AffCom,
VOLUME = "16",
YEAR = "2025",
NUMBER = "3",
MONTH = "July",
PAGES = "1290-1306",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372973"}
@article{bb378880,
AUTHOR = "Yang, Y. and Zhou, C.",
TITLE = "DPARNet-RSE: Toward Angular Region-Customizable Speech Extraction",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3779-3783",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372974"}
@article{bb378881,
AUTHOR = "Zhao, Z.Y. and Peng, Y. and Camilleri, K. and Kong, W.Z. and Cichocki, A.",
TITLE = "Imagined Speech Decoding by Learning Consensus Graph From RKHS-Based
Multi-View EEG Features",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3944-3948",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372975"}
@article{bb378882,
AUTHOR = "Tan, Z.W. and Reju, V.G. and Tewari, R.C. and Ding, R.T. and Khong, A.W.H.",
TITLE = "Joint Enhancement and Bandwidth Extension for Radar Through-Barrier
Speech Acquisition",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "176-180",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372976"}
@article{bb378883,
AUTHOR = "Fu, R. and Tang, L. and Tian, H. and Chang, C.C.",
TITLE = "Fuzzy-Clustering-Based Domain Adaptation for Speech Steganalysis in
Dynamic Scenarios",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "366-370",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372977"}
@article{bb378884,
AUTHOR = "Wang, T. and Yi, J.Y. and Fu, R. and Qiang, C.Y. and Chong, D. and Wang, C. and Dai, D.Y. and Wen, Z.Q. and Tao, J.H.",
TITLE = "SpeechPalette: A Comprehensive Speech Editing Method for Text-Based
Speech Editing, One-Shot TTS and Attributes Editing",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "2596-2609",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372978"}
@article{bb378885,
AUTHOR = "Hu, H.Q. and Liao, Y. and Cai, S.Q. and Li, H.Z.",
TITLE = "The effect of speech representations on EEG-based auditory attention
detection",
JOURNAL = PRL,
VOLUME = "203",
YEAR = "2026",
PAGES = "146-151",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372979"}
@article{bb378886,
AUTHOR = "Kim, D. and Jung, S.K.",
TITLE = "Bin-Wise Zone-Based Speech Presence Detection With Metric-Aligned DCF
Optimization",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "1471-1475",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372980"}
@inproceedings{bb378887,
AUTHOR = "Wani, T.M. and Amerini, I.",
TITLE = "Deepfakes Audio Detection Leveraging Audio Spectrogram and
Convolutional Neural Networks",
BOOKTITLE = CIAP23,
YEAR = "2023",
PAGES = "II:156-167",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372981"}
@inproceedings{bb378888,
AUTHOR = "Choi, S. and Oh, S. and Yang, J. and Lee, Y. and Kwak, I.Y.",
TITLE = "Light-weight Frequency Information Aware Neural Network Architecture
for Voice Spoofing Detection",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "477-483",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372982"}
@inproceedings{bb378889,
AUTHOR = "Li, X. and Hu, X. and Chen, X. and Pan, H. and Niu, K.",
TITLE = "Deep Speaker Embedding Using Hybrid Network of Multi-Feature
Aggregation and Multi-Loss Fusion for TI-SV",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "506-512",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372983"}
@inproceedings{bb378890,
AUTHOR = "Zhang, B. and Sim, T.",
TITLE = "Localizing Fake Segments in Speech",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "3224-3230",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372984"}
@inproceedings{bb378891,
AUTHOR = "Teng, Z.W. and Fu, Q. and White, J. and Powell, M.E. and Schmidt, D.C.",
TITLE = "ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof
Speech Detection",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "692-698",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372985"}
@inproceedings{bb378892,
AUTHOR = "Stefanov, K. and Adiban, M. and Salvi, G.",
TITLE = "Spatial Bias in Vision-Based Voice Activity Detection",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "10433-10440",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372986"}
@inproceedings{bb378893,
AUTHOR = "Barros, F. and Conde, A. and Soares, S.C. and Neves, A.J.R. and Silva, S.",
TITLE = "Understanding Public Speakers' Performance:
First Contributions to Support a Computational Approach",
BOOKTITLE = ICIAR20,
YEAR = "2020",
PAGES = "I:343-355",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372987"}
@inproceedings{bb378894,
AUTHOR = "Bilkova, Z. and Novozamsky, A. and Dominec, A. and Gresko, S. and Zitova, B. and Paroubkova, M.",
TITLE = "Automatic Evaluation of Speech Therapy Exercises Based on Image Data",
BOOKTITLE = ICIAR19,
YEAR = "2019",
PAGES = "I:397-404",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372988"}
@inproceedings{bb378895,
AUTHOR = "Dai, J.J. and Dixon, S.",
TITLE = "Understanding Intonation Trajectories and Patterns of Vocal Notes",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "II:243-253",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372989"}
@inproceedings{bb378896,
AUTHOR = "Zheng, S. and Wang, J. and Xiao, J. and Hsu, W. and Glass, J.",
TITLE = "A Noise-Robust Self-Adaptive Multitarget Speaker Detection System",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "1068-1072",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372990"}
@inproceedings{bb378897,
AUTHOR = "Athanasopoulos, G. and Hagihara, K. and Cierro, A. and Guerit, R. and Chatelain, J. and Lucas, C. and Macq, B.",
TITLE = "3D immersive karaoke for the learning of foreign language
pronunciation",
BOOKTITLE = IC3D17,
YEAR = "2017",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372991"}
@inproceedings{bb378898,
AUTHOR = "Serras, M. and Torres, M.I. and del Pozo, A.",
TITLE = "Online Learning of Attributed Bi-Automata for Dialogue Management in
Spoken Dialogue Systems",
BOOKTITLE = IbPRIA17,
YEAR = "2017",
PAGES = "22-31",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372992"}
@inproceedings{bb378899,
AUTHOR = "Nagpal, A. and Patil, H.A.",
TITLE = "Novel Gammatone Filterbank Based Spectro-Temporal Features for Robust
Phoneme Recognition",
BOOKTITLE = PReMI17,
YEAR = "2017",
PAGES = "342-350",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT372993"}
Last update:Apr 23, 2026 at 15:05:02