@article{bb370400,
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#TT364552"}
@article{bb370401,
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#TT364553"}
@article{bb370402,
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#TT364554"}
@inproceedings{bb370403,
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#TT364555"}
@article{bb370404,
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#TT364556"}
@article{bb370405,
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#TT364557"}
@article{bb370406,
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#TT364558"}
@article{bb370407,
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#TT364559"}
@article{bb370408,
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#TT364560"}
@article{bb370409,
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#TT364561"}
@article{bb370410,
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#TT364562"}
@article{bb370411,
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#TT364563"}
@article{bb370412,
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#TT364564"}
@article{bb370413,
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#TT364565"}
@article{bb370414,
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#TT364566"}
@inproceedings{bb370415,
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#TT364567"}
@article{bb370416,
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#TT364568"}
@article{bb370417,
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#TT364569"}
@article{bb370418,
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#TT364570"}
@article{bb370419,
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#TT364571"}
@article{bb370420,
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#TT364572"}
@article{bb370421,
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#TT364573"}
@article{bb370422,
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#TT364574"}
@article{bb370423,
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#TT364575"}
@article{bb370424,
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#TT364576"}
@article{bb370425,
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#TT364577"}
@article{bb370426,
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#TT364578"}
@article{bb370427,
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#TT364579"}
@article{bb370428,
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#TT364580"}
@article{bb370429,
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#TT364581"}
@article{bb370430,
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#TT364582"}
@article{bb370431,
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#TT364583"}
@article{bb370432,
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#TT364584"}
@article{bb370433,
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#TT364585"}
@article{bb370434,
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#TT364586"}
@article{bb370435,
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#TT364587"}
@article{bb370436,
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#TT364588"}
@article{bb370437,
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#TT364589"}
@article{bb370438,
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#TT364590"}
@article{bb370439,
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#TT364591"}
@article{bb370440,
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#TT364592"}
@article{bb370441,
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#TT364593"}
@article{bb370442,
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#TT364594"}
@article{bb370443,
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#TT364595"}
@article{bb370444,
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#TT364596"}
@article{bb370445,
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#TT364597"}
@article{bb370446,
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#TT364598"}
@article{bb370447,
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#TT364599"}
@article{bb370448,
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#TT364600"}
@article{bb370449,
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#TT364601"}
@article{bb370450,
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#TT364602"}
@inproceedings{bb370451,
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#TT364603"}
@article{bb370452,
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#TT364604"}
@article{bb370453,
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#TT364605"}
@article{bb370454,
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#TT364606"}
@article{bb370455,
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#TT364607"}
@article{bb370456,
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#TT364608"}
@article{bb370457,
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#TT364609"}
@article{bb370458,
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#TT364610"}
@article{bb370459,
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#TT364611"}
@article{bb370460,
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#TT364612"}
@article{bb370461,
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#TT364613"}
@article{bb370462,
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#TT364614"}
@article{bb370463,
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#TT364615"}
@article{bb370464,
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#TT364616"}
@article{bb370465,
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#TT364617"}
@article{bb370466,
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#TT364618"}
@article{bb370467,
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#TT364619"}
@article{bb370468,
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#TT364620"}
@article{bb370469,
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#TT364621"}
@article{bb370470,
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#TT364622"}
@article{bb370471,
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#TT364623"}
@article{bb370472,
AUTHOR = "Zhao, Z. 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#TT364624"}
@inproceedings{bb370473,
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#TT364625"}
@inproceedings{bb370474,
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#TT364626"}
@inproceedings{bb370475,
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#TT364627"}
@inproceedings{bb370476,
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#TT364628"}
@inproceedings{bb370477,
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#TT364629"}
@inproceedings{bb370478,
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#TT364630"}
@inproceedings{bb370479,
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#TT364631"}
@inproceedings{bb370480,
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#TT364632"}
@inproceedings{bb370481,
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#TT364633"}
@inproceedings{bb370482,
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#TT364634"}
@inproceedings{bb370483,
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#TT364635"}
@inproceedings{bb370484,
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#TT364636"}
@inproceedings{bb370485,
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#TT364637"}
@inproceedings{bb370486,
AUTHOR = "Grachev, A.M. and Ignatov, D.I. and Savchenko, A.V.",
TITLE = "Neural Networks Compression for Language Modeling",
BOOKTITLE = PReMI17,
YEAR = "2017",
PAGES = "351-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364638"}
@inproceedings{bb370487,
AUTHOR = "Zhang, L. and Chen, J.X. and Luo, Y. and Fu, J.F. and Ye, Z.F.",
TITLE = "Supervised single-channel speech dereverberation and denoising using
a two-stage processing",
BOOKTITLE = ICIVC17,
YEAR = "2017",
PAGES = "818-822",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364639"}
@inproceedings{bb370488,
AUTHOR = "Bedoui, A. and Ben Jebara, S.",
TITLE = "On the use of opening phase slopes of the glottal signal to
characterize unilateral vocal folds paralysis",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "41-46",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364640"}
@inproceedings{bb370489,
AUTHOR = "Ben Ali, F. and Djaziri Larbi, S.",
TITLE = "A very low bit rate codec for wide band speech based on a long-term
perceptual harmonic plus noise model",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "71-76",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364641"}
@inproceedings{bb370490,
AUTHOR = "Ferreira, A.",
TITLE = "Implantation of voicing on whispered speech using frequency-domain
parametric modelling of source and filter information",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "159-166",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364642"}
@inproceedings{bb370491,
AUTHOR = "Pozzebon, A. and Biliotti, F. and Calamai, S.",
TITLE = "Places Speaking with Their Own Voices. A Case Study from the Gra.fo
Archives",
BOOKTITLE = EuroMed16,
YEAR = "2016",
PAGES = "II: 232-239",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364643"}
@inproceedings{bb370492,
AUTHOR = "Vlaj, D. and Kos, M. and Kacic, Z.",
TITLE = "Quick and efficient definition of hangbefore and hangover criteria
for voice activity detection",
BOOKTITLE = WSSIP16,
YEAR = "2016",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364644"}
@inproceedings{bb370493,
AUTHOR = "Ballesteros L, D.M. and Renza, D. and Camacho, S.",
TITLE = "High Scrambling Degree in Audio Through Imitation of an Unintelligible
Signal",
BOOKTITLE = MCPR16,
YEAR = "2016",
PAGES = "251-259",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364645"}
@inproceedings{bb370494,
AUTHOR = "Onchis, D.M. and Real, P.",
TITLE = "On Homotopy Continuation for Speech Restoration",
BOOKTITLE = CTIC16,
YEAR = "2016",
PAGES = "152-156",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364646"}
@inproceedings{bb370495,
AUTHOR = "Dubey, M.L. and Shultz, P.F. and Kenyon, G.T.",
TITLE = "Learning phase-rich features from streaming auditory images",
BOOKTITLE = Southwest16,
YEAR = "2016",
PAGES = "73-76",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364647"}
@inproceedings{bb370496,
AUTHOR = "Montalvo, A. and Costa, Y.M.G. and Calvo, J.R.",
TITLE = "Language Identification Using Spectrogram Texture",
BOOKTITLE = CIARP15,
YEAR = "2015",
PAGES = "543-550",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364648"}
@inproceedings{bb370497,
AUTHOR = "Aizezi, Y. and Jamal, A. and Mamat, D. and Abdurexit, R. and Ubul, K.",
TITLE = "Analytical Method and Research of Uyghur Language Chunks Based on
Digital Forensics",
BOOKTITLE = ISCA15,
YEAR = "2015",
PAGES = "258-266",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364649"}
@inproceedings{bb370498,
AUTHOR = "Hammami, N. and Bedda, M. and Farah, N. and Mansouri, S.",
TITLE = "R-Letter disorder diagnosis (R-LDD): Arabic speech database
development for automatic diagnosis of childhood speech disorders
(Case study)",
BOOKTITLE = ISCV15,
YEAR = "2015",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364650"}
@inproceedings{bb370499,
AUTHOR = "Nakajima, J. and Kimura, A. and Sugimoto, A. and Kashino, K.",
TITLE = "Visual Attention Driven by Auditory Cues",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "II: 74-86",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT364651"}
Last update:Nov 26, 2025 at 20:24:09