@article{bb388300,
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#TT382362"}
@article{bb388301,
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#TT382363"}
@article{bb388302,
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#TT382364"}
@article{bb388303,
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#TT382365"}
@article{bb388304,
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#TT382366"}
@article{bb388305,
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#TT382367"}
@article{bb388306,
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#TT382368"}
@article{bb388307,
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#TT382369"}
@article{bb388308,
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#TT382370"}
@article{bb388309,
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#TT382371"}
@article{bb388310,
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#TT382372"}
@article{bb388311,
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#TT382373"}
@article{bb388312,
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#TT382374"}
@article{bb388313,
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#TT382375"}
@article{bb388314,
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#TT382376"}
@article{bb388315,
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#TT382377"}
@article{bb388316,
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#TT382378"}
@article{bb388317,
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#TT382379"}
@article{bb388318,
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#TT382380"}
@article{bb388319,
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#TT382381"}
@article{bb388320,
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#TT382382"}
@article{bb388321,
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#TT382383"}
@article{bb388322,
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#TT382384"}
@article{bb388323,
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#TT382385"}
@article{bb388324,
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#TT382386"}
@article{bb388325,
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#TT382387"}
@article{bb388326,
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#TT382388"}
@article{bb388327,
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#TT382389"}
@article{bb388328,
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#TT382390"}
@article{bb388329,
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#TT382391"}
@inproceedings{bb388330,
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#TT382392"}
@article{bb388331,
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#TT382393"}
@article{bb388332,
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#TT382394"}
@article{bb388333,
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#TT382395"}
@article{bb388334,
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#TT382396"}
@article{bb388335,
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#TT382397"}
@article{bb388336,
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#TT382398"}
@article{bb388337,
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#TT382399"}
@article{bb388338,
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#TT382400"}
@article{bb388339,
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#TT382401"}
@article{bb388340,
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#TT382402"}
@article{bb388341,
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#TT382403"}
@article{bb388342,
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#TT382404"}
@article{bb388343,
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#TT382405"}
@article{bb388344,
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#TT382406"}
@article{bb388345,
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#TT382407"}
@article{bb388346,
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#TT382408"}
@article{bb388347,
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#TT382409"}
@article{bb388348,
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#TT382410"}
@article{bb388349,
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#TT382411"}
@article{bb388350,
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#TT382412"}
@article{bb388351,
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#TT382413"}
@article{bb388352,
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#TT382414"}
@article{bb388353,
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#TT382415"}
@article{bb388354,
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#TT382416"}
@article{bb388355,
AUTHOR = "Zhang, W.J. and Qian, Y.K. and Cao, Y. and He, C.J. and Xu, S. and Wang, M.J.",
TITLE = "CARVE: Content-Adaptive Rate-Variable Encoding for Neural Speech
Codecs",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2036-2040",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382417"}
@article{bb388356,
AUTHOR = "Liu, W. and Huang, G.P. and Jin, J. and Luo, X. and Makino, S.",
TITLE = "Revisiting Steering Limitations of LCMV Beamforming for Circular
Microphone Arrays and a Mainlobe-Controlled Solution",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2750-2754",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382418"}
@article{bb388357,
AUTHOR = "Dai, L.L. and Li, A.D. and Lei, T. and Li, X.D. and Zheng, C.S.",
TITLE = "Rethinking the Joint Estimation of Magnitude and Phase for
Time-Frequency Domain Neural Vocoders",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2770-2774",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382419"}
@article{bb388358,
AUTHOR = "van Rensburg, K.J. and van Niekerk, B. and Kamper, H.",
TITLE = "Interpreting Speaker Characteristics in the Dimensions of
Self-Supervised Speech Features",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3132-3136",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382420"}
@article{bb388359,
AUTHOR = "Gohari, M. and Salvi, D. and Bestagini, P. and Adami, N.",
TITLE = "Interpretable detection of singing voice manipulations using
audio-language models",
JOURNAL = CVIU,
VOLUME = "271",
YEAR = "2026",
PAGES = "104898",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382421"}
@inproceedings{bb388360,
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#TT382422"}
@inproceedings{bb388361,
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#TT382423"}
@inproceedings{bb388362,
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#TT382424"}
@inproceedings{bb388363,
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#TT382425"}
@inproceedings{bb388364,
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#TT382426"}
@inproceedings{bb388365,
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#TT382427"}
@inproceedings{bb388366,
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#TT382428"}
@inproceedings{bb388367,
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#TT382429"}
@inproceedings{bb388368,
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#TT382430"}
@inproceedings{bb388369,
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#TT382431"}
@inproceedings{bb388370,
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#TT382432"}
@inproceedings{bb388371,
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#TT382433"}
@inproceedings{bb388372,
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#TT382434"}
@inproceedings{bb388373,
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#TT382435"}
@inproceedings{bb388374,
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#TT382436"}
@inproceedings{bb388375,
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#TT382437"}
@inproceedings{bb388376,
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#TT382438"}
@inproceedings{bb388377,
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#TT382439"}
@inproceedings{bb388378,
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#TT382440"}
@inproceedings{bb388379,
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#TT382441"}
@inproceedings{bb388380,
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#TT382442"}
@inproceedings{bb388381,
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#TT382443"}
@inproceedings{bb388382,
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#TT382444"}
@inproceedings{bb388383,
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#TT382445"}
@inproceedings{bb388384,
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#TT382446"}
@inproceedings{bb388385,
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#TT382447"}
@inproceedings{bb388386,
AUTHOR = "Ishikura, K. and Uemura, A. and Katto, J.",
TITLE = "Live Version Identification with Audio Scene Detection",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 408-417",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382448"}
@inproceedings{bb388387,
AUTHOR = "Xie, S.B. and Yang, Y.H. and Hu, R.M. and Wang, Y.Y. and Yu, H.J. and Dong, S.L. and Gao, L. and Yang, C.",
TITLE = "Signal-Aware Parametric Quality Model for Audio and Speech over IP
Networks",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 487-497",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382449"}
@inproceedings{bb388388,
AUTHOR = "Xue, L. and Su, F.",
TITLE = "Auditory Scene Classification with Deep Belief Network",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 348-359",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382450"}
@inproceedings{bb388389,
AUTHOR = "Tu, M. and Xie, X. and Na, X.Y.",
TITLE = "Computational Auditory Scene Analysis Based Voice Activity Detection",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "797-802",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382451"}
@inproceedings{bb388390,
AUTHOR = "Lu, T. and Weng, Y.B. and Wang, G.Y.",
TITLE = "Audiotory Movie Summarization by Detecting Scene Changes and Sound
Events",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "756-760",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382452"}
@inproceedings{bb388391,
AUTHOR = "Nguyen Son, H.Q. and Hoang, A.T. and Tran, M.T. and Yoshiura, H. and Sonehara, N. and Echizen, I.",
TITLE = "Anonymizing Temporal Phrases in Natural Language Text to be Posted on
Social Networking Services",
BOOKTITLE = IWDW13,
YEAR = "2013",
PAGES = "437-451",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382453"}
@inproceedings{bb388392,
AUTHOR = "Maka, T. and Dziurzanski, P.",
TITLE = "Feature contours fusion for determining segment boundaries in audio
data",
BOOKTITLE = WSSIP14,
YEAR = "2014",
PAGES = "111-114",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382454"}
@inproceedings{bb388393,
AUTHOR = "Souza, D. and Saturnino, L. and Maciel, A.M.A.",
TITLE = "A portability evaluation of Brazilian Portuguese voices produced with
MARY TTS",
BOOKTITLE = WSSIP14,
YEAR = "2014",
PAGES = "95-98",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382455"}
@inproceedings{bb388394,
AUTHOR = "Frid, A. and Lavner, Y.Z.",
TITLE = "Spectral and textural features for automatic classification of
fricatives using SVM",
BOOKTITLE = WSSIP14,
YEAR = "2014",
PAGES = "99-102",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382456"}
@inproceedings{bb388395,
AUTHOR = "Savchenko, A.V.",
TITLE = "Semi-automated Speaker Adaptation:
How to Control the Quality of Adaptation?",
BOOKTITLE = ICISP14,
YEAR = "2014",
PAGES = "638-646",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382457"}
@inproceedings{bb388396,
AUTHOR = "Merazka, F.",
TITLE = "Wideband Speech Encryption Based Arnold Cat Map for AMR-WB G.722.2
Codec",
BOOKTITLE = ICISP14,
YEAR = "2014",
PAGES = "658-664",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382458"}
@inproceedings{bb388397,
AUTHOR = "Souli, S. and Lachiri, Z. and Kuznietsov, A.",
TITLE = "Using Three Reassigned Spectrogram Patches and Log-Gabor Filter for
Audio Surveillance Application",
BOOKTITLE = CIARP13,
YEAR = "2013",
PAGES = "I:527-534",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382459"}
@inproceedings{bb388398,
AUTHOR = "Joseph, S.M. and Babu, A.P.",
TITLE = "Continuous speech coding using coiflets wavelet",
BOOKTITLE = ICSIPR13,
YEAR = "2013",
PAGES = "253-257",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382460"}
@inproceedings{bb388399,
AUTHOR = "Nivedita, D. and Kavita, T. and Zadgaonkar, A.S.",
TITLE = "First degree heart block determination from speech analysis",
BOOKTITLE = ICSIPR13,
YEAR = "2013",
PAGES = "103-106",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT382461"}
Last update:Oct 8, 2026 at 11:03:09