@article{bb376500,
AUTHOR = "Lee, J. and Skoglund, J. and Shabestary, T. and Kang, H.",
TITLE = "Phase-Sensitive Joint Learning Algorithms for Deep Learning-Based
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "8",
MONTH = "August",
PAGES = "1276-1280",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370603"}
@article{bb376501,
AUTHOR = "Martin Donas, J.M. and Gomez, A.M. and Gonzalez, J.A. and Peinado, A.M.",
TITLE = "A Deep Learning Loss Function Based on the Perceptual Evaluation of
the Speech Quality",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "11",
MONTH = "November",
PAGES = "1680-1684",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370604"}
@article{bb376502,
AUTHOR = "Kim, G. and Lee, H. and Kim, B. and Oh, S. and Lee, S.",
TITLE = "Unpaired Speech Enhancement by Acoustic and Adversarial Supervision
for Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "1",
MONTH = "January",
PAGES = "159-163",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370605"}
@article{bb376503,
AUTHOR = "Lei, P. and Chen, M.L. and Wang, J.",
TITLE = "Speech enhancement for in-vehicle voice control systems using wavelet
analysis and blind source separation",
JOURNAL = IET-ITS,
VOLUME = "13",
YEAR = "2019",
NUMBER = "4",
MONTH = "April",
PAGES = "693-702",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370606"}
@article{bb376504,
AUTHOR = "Ram, R. and Mohanty, M.N.",
TITLE = "Use of radial basis function network with discrete wavelet transform
for speech enhancement",
JOURNAL = IJCVR,
VOLUME = "9",
YEAR = "2019",
NUMBER = "2",
PAGES = "207-223",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370607"}
@article{bb376505,
AUTHOR = "Kim, J. and Hahn, M.",
TITLE = "Speech Enhancement Using a Two-Stage Network for an Efficient
Boosting Strategy",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "5",
MONTH = "May",
PAGES = "770-774",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370608"}
@article{bb376506,
AUTHOR = "Nakatani, T. and Kinoshita, K.",
TITLE = "A Unified Convolutional Beamformer for Simultaneous Denoising and
Dereverberation",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "6",
MONTH = "June",
PAGES = "903-907",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370609"}
@article{bb376507,
AUTHOR = "Li, X. and Leglaive, S. and Girin, L. and Horaud, R.",
TITLE = "Audio-Noise Power Spectral Density Estimation Using Long Short-Term
Memory",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "6",
MONTH = "June",
PAGES = "918-922",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370610"}
@article{bb376508,
AUTHOR = "Fu, S. and Liao, C. and Tsao, Y.",
TITLE = "Learning With Learned Loss Function: Speech Enhancement With
Quality-Net to Improve Perceptual Evaluation of Speech Quality",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "26-30",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370611"}
@article{bb376509,
AUTHOR = "Wu, J. and Yu, C. and Fu, S. and Liu, C. and Chien, S. and Tsao, Y.",
TITLE = "Increasing Compactness of Deep Learning Based Speech Enhancement
Models With Parameter Pruning and Quantization Techniques",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "12",
MONTH = "December",
PAGES = "1887-1891",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370612"}
@article{bb376510,
AUTHOR = "Yu, C. and Hung, K. and Wang, S. and Tsao, Y. and Hung, J.",
TITLE = "Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1035-1039",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370613"}
@article{bb376511,
AUTHOR = "Hsieh, T.A. and Wang, H.M. and Lu, X. and Tsao, Y.",
TITLE = "WaveCRN: An Efficient Convolutional Recurrent Neural Network for
End-to-End Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "2149-2153",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370614"}
@article{bb376512,
AUTHOR = "Siniscalchi, S.M.",
TITLE = "Vector-to-Vector Regression via Distributional Loss for Speech
Enhancement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "254-258",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370615"}
@article{bb376513,
AUTHOR = "Cui, Z. and Bao, C.C.",
TITLE = "Power Exponent Based Weighting Criterion for DNN-Based Mask
Approximation in Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "618-622",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370616"}
@article{bb376514,
AUTHOR = "Witkowski, M. and Kowalczyk, K.",
TITLE = "Split Bregman Approach to Linear Prediction Based Dereverberation
With Enforced Speech Sparsity",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "942-946",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370617"}
@article{bb376515,
AUTHOR = "Pan, N.N. and Wang, Y.Z. and Chen, J.D. and Benesty, J.",
TITLE = "A Single-Input/Binaural-Output Antiphasic Speech Enhancement Method
for Speech Intelligibility Improvement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1445-1449",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370618"}
@article{bb376516,
AUTHOR = "Xiang, X.X. and Zhang, X.J. and Chen, H.Z.",
TITLE = "A Convolutional Network With Multi-Scale and Attention Mechanisms for
End-to-End Single-Channel Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1455-1459",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370619"}
@article{bb376517,
AUTHOR = "Xiang, X.X. and Zhang, X.J. and Chen, H.Z.",
TITLE = "Two-Stage Learning and Fusion Network With Noise Aware for
Time-Domain Monaural Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1754-1758",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370620"}
@article{bb376518,
AUTHOR = "Li, G. and Wang, X.C. and Hu, R.M. and Zhang, H.Y. and Ke, S.F.",
TITLE = "Intelligibility Enhancement Via Normal-to-Lombard Speech Conversion
With Long Short-Term Memory Network and Bayesian Gaussian Mixture
Model",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "3035-3047",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370621"}
@article{bb376519,
AUTHOR = "Cheng, L.B. and Li, J.F. and Yan, Y.H.",
TITLE = "FSCNet: Feature-Specific Convolution Neural Network for Real-Time
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1958-1962",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370622"}
@article{bb376520,
AUTHOR = "Tai, W.X. and Lan, T. and Wang, Q.H. and Liu, Q.",
TITLE = "IDANet: An Information Distillation and Aggregation Network for
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1998-2002",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370623"}
@article{bb376521,
AUTHOR = "Wang, Z.Q. and Wichern, G. and Le Roux, J.",
TITLE = "On the Compensation Between Magnitude and Phase in Speech Separation",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "2018-2022",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370624"}
@article{bb376522,
AUTHOR = "Xiang, X.X. and Zhang, X.J. and Chen, H.Z.",
TITLE = "A Nested U-Net With Self-Attention and Dense Connectivity for
Monaural Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "105-109",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370625"}
@article{bb376523,
AUTHOR = "Wang, Z.Q. and Watanabe, S.",
TITLE = "Improving Frame-Online Neural Speech Enhancement With
Overlapped-Frame Prediction",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1422-1426",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370626"}
@article{bb376524,
AUTHOR = "Kim, H. and Kang, K. and Shin, J.W.",
TITLE = "Factorized MVDR Deep Beamforming for Multi-Channel Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1898-1902",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370627"}
@article{bb376525,
AUTHOR = "Fras, M. and Kowalczyk, K.",
TITLE = "Convolutional Weighted Parametric Multichannel Wiener Filter for
Reverberant Source Separation",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "1928-1932",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370628"}
@article{bb376526,
AUTHOR = "Hwang, S. and Lee, E. and Jang, I. and Shin, J.W.",
TITLE = "Alias-and-Separate: Wideband Speech Coding Using Sub-Nyquist Sampling
and Speech Separation",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2003-2007",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370629"}
@article{bb376527,
AUTHOR = "Yadav, S.K. and George, N.V.",
TITLE = "Sparse Distortionless Modal Beamforming for Spherical Microphone
Arrays",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2068-2072",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370630"}
@article{bb376528,
AUTHOR = "Lee, J.Y. and Kang, H.G.",
TITLE = "Two-Stage Refinement of Magnitude and Complex Spectra for Real-Time
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2188-2192",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370631"}
@article{bb376529,
AUTHOR = "Yu, R.X. and Zhao, Z.W. and Ye, Z.F.",
TITLE = "PFRNet: Dual-Branch Progressive Fusion Rectification Network for
Monaural Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2358-2362",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370632"}
@article{bb376530,
AUTHOR = "Rosenbaum, T. and Cohen, I. and Winebrand, E. and Gabso, O.",
TITLE = "Differentiable Mean Opinion Score Regularization for Perceptual
Speech Enhancement",
JOURNAL = PRL,
VOLUME = "166",
YEAR = "2023",
PAGES = "159-163",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370633"}
@article{bb376531,
AUTHOR = "Lee, D. and Choi, J.W.",
TITLE = "DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "155-159",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370634"}
@article{bb376532,
AUTHOR = "Wang, T.T. and Pan, Z. and Ge, M. and Yang, Z. and Li, H.Z.",
TITLE = "Time-Domain Speech Separation Networks With Graph Encoding Auxiliary",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "110-114",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370635"}
@article{bb376533,
AUTHOR = "Duan, Y. and Ren, J.F. and Yu, H. and Jiang, X.D.",
TITLE = "GAN-in-GAN for Monaural Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "853-857",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370636"}
@article{bb376534,
AUTHOR = "Ai, Y. and Lu, Y.X. and Ling, Z.H.",
TITLE = "Long-Frame-Shift Neural Speech Phase Prediction With Spectral
Continuity Enhancement and Interpolation Error Compensation",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1097-1101",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370637"}
@article{bb376535,
AUTHOR = "Xiong, J.W. and Zhou, Y. and Zhang, P. and Xie, L. and Huang, W. and Zha, Y.F.",
TITLE = "Look&listen: Multi-Modal Correlation Learning for Active Speaker
Detection and Speech Enhancement",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "5800-5812",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370638"}
@article{bb376536,
AUTHOR = "Liang, X.W. and Zhang, L. and Wu, Z.Y. and Xu, R.F.",
TITLE = "Lite-RTSE: Exploring a Cost-Effective Lite DNN Model for Real-Time
Speech Enhancement in RTC Scenarios",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1697-1701",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370639"}
@article{bb376537,
AUTHOR = "Yechuri, S. and Vanabathina, S.D.",
TITLE = "Genetic Algorithm-Based Adaptive Wiener Gain for Speech Enhancement
Using an Iterative Posterior NMF",
JOURNAL = IJIG,
VOLUME = "23",
YEAR = "2023",
NUMBER = "6 2023",
PAGES = "2350054",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370640"}
@article{bb376538,
AUTHOR = "O'Shaughnessy, D.",
TITLE = "Speech Enhancement: A Review of Modern Methods",
JOURNAL = HMS,
VOLUME = "54",
YEAR = "2024",
NUMBER = "1",
MONTH = "February",
PAGES = "110-120",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370641"}
@article{bb376539,
AUTHOR = "Xu, X.",
TITLE = "Improving Monaural Speech Enhancement by Mapping to Fixed Simulation
Space With Knowledge Distillation",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "386-390",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370642"}
@article{bb376540,
AUTHOR = "Xiang, B. and Mao, W.Y. and Tan, K.J. and Lu, H.X.",
TITLE = "CAT-DUnet: Enhancing Speech Dereverberation via Feature Fusion and
Structural Similarity Loss",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "456-460",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370643"}
@article{bb376541,
AUTHOR = "Park, H.J. and Shin, W. and Kim, J.S. and Han, S.W.",
TITLE = "Leveraging Non-Causal Knowledge via Cross-Network Knowledge
Distillation for Real-Time Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1129-1133",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370644"}
@article{bb376542,
AUTHOR = "Jannu, C. and Vanambathina, S.D.",
TITLE = "Shuffle Attention U-Net for Speech Enhancement in Time Domain",
JOURNAL = IJIG,
VOLUME = "24",
YEAR = "2024",
NUMBER = "4",
MONTH = "July",
PAGES = "2450043",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370645"}
@article{bb376543,
AUTHOR = "Han, R. and Xu, W.M. and Zhang, Z. and Liu, M.S. and Xie, L.",
TITLE = "Distil-DCCRN: A Small-Footprint DCCRN Leveraging Feature-Based
Knowledge Distillation in Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2075-2079",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370646"}
@article{bb376544,
AUTHOR = "Gonzalez, P. and Tan, Z.H. and Ostergaard, J. and Jensen, J. and Alstrom, T.S. and May, T.",
TITLE = "The Effect of Training Dataset Size on Discriminative and
Diffusion-Based Speech Enhancement Systems",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2225-2229",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370647"}
@article{bb376545,
AUTHOR = "Quan, C.S. and Li, X.F.",
TITLE = "Multichannel Long-Term Streaming Neural Speech Enhancement for Static
and Moving Speakers",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2295-2299",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370648"}
@article{bb376546,
AUTHOR = "Hao, Y. and Xiong, F.F. and Li, B. and Ding, N. and Feng, J.",
TITLE = "EMDSQA: A Neural Speech Quality Assessment Model With Speaker
Embedding",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "3064-3068",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370649"}
@article{bb376547,
AUTHOR = "Yang, Z. and Song, X. and Chen, J. and Richard, C. and Cohen, I.",
TITLE = "Learning Noise Adapters for Incremental Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2915-2919",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370650"}
@article{bb376548,
AUTHOR = "Jannu, C. and Vanambathina, S.D.",
TITLE = "Self-Attention-Based Convolutional GRU for Enhancement of Adversarial
Speech Examples",
JOURNAL = IJIG,
VOLUME = "24",
YEAR = "2024",
NUMBER = "6",
MONTH = "November",
PAGES = "2450053",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370651"}
@article{bb376549,
AUTHOR = "Guo, Z. and Du, J. and Siniscalchi, S.M. and Pan, J. and Liu, Q.F.",
TITLE = "Controllable Conformer for Speech Enhancement and Recognition",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "156-160",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370652"}
@article{bb376550,
AUTHOR = "Wang, C.Z. and Gu, J.J. and Yao, D.D. and Li, J.F. and Yan, Y.H.",
TITLE = "GALD-SE: Guided Anisotropic Lightweight Diffusion for Efficient
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "426-430",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370653"}
@article{bb376551,
AUTHOR = "Hou, Z. and Lei, T. and Hu, Q. and Cao, Z.Z. and Lu, J.",
TITLE = "SNR-Progressive Model With Harmonic Compensation for Low-SNR Speech
Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "476-480",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370654"}
@article{bb376552,
AUTHOR = "Jannu, C. and Vanambathina, S.D.",
TITLE = "An Overview of Speech Enhancement Based on Deep Learning Techniques",
JOURNAL = IJIG,
VOLUME = "25",
YEAR = "2025",
NUMBER = "1",
MONTH = "Jan",
PAGES = "2550001",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370655"}
@article{bb376553,
AUTHOR = "Zhou, H. and Zhou, Y. and Cheng, Z.H. and Zhao, Y. and Liu, Y.",
TITLE = "Improved Encoder-Decoder Architecture With Human-Like Perception
Attention for Monaural Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1670-1674",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370656"}
@article{bb376554,
AUTHOR = "Yechuri, S. and Vanabathina, S.D.",
TITLE = "Speech Enhancement: A Review of Different Deep Learning Methods",
JOURNAL = IJIG,
VOLUME = "25",
YEAR = "2025",
NUMBER = "3",
MONTH = "May",
PAGES = "2550024",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370657"}
@article{bb376555,
AUTHOR = "Lei, Y. and Luo, X. and Tai, W.X. and Zhou, F.",
TITLE = "Progressive Skip Connection Improves Consistency of Diffusion-Based
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1650-1654",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370658"}
@article{bb376556,
AUTHOR = "Xu, S. and Cao, Y.H. and Zhang, W.J. and Zhang, Z. and Wang, M.J.",
TITLE = "FSTF-AN: Fused Sparse Temporal-Frequency Attentive Network for
Multi-Channel Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2124-2128",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370659"}
@article{bb376557,
AUTHOR = "Ma, H. and Chen, R. and Zhang, X.L. and Liu, J. and Li, X.L.",
TITLE = "Enhancing Intelligibility for Generative Target Speech Extraction via
Joint Optimization With Target Speaker ASR",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2309-2313",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370660"}
@article{bb376558,
AUTHOR = "Sadeghi, M. and Ayilo, J.E. and Serizel, R. and Alameda Pineda, X.",
TITLE = "Posterior Transition Modeling for Unsupervised Diffusion-Based Speech
Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2694-2698",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370661"}
@article{bb376559,
AUTHOR = "Yang, D.H. and Lee, J. and Chang, J.H.",
TITLE = "Tokenized Generative Speech Enhancement With Language Model and Flow
Matching",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2828-2832",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370662"}
@article{bb376560,
AUTHOR = "Yang, D.H. and Chang, J.H.",
TITLE = "Latent-Level Enhancement With Flow Matching for Robust Automatic
Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "589-593",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370663"}
@article{bb376561,
AUTHOR = "Han, Y. and Chen, H. and Liu, L.J. and Du, J.",
TITLE = "Dual-Branch Codec With Orthogonality Constraint and Knowledge
Distillation for Noisy Environment",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3017-3021",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370664"}
@article{bb376562,
AUTHOR = "Hua, H. and Shang, Z.Q. and Li, X. and Yang, C. and Zhang, P.Y.",
TITLE = "Flexpéro: Flexible Expressive Zero-Shot Speech Refinement via
In-Context Learning",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3122-3126",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370665"}
@article{bb376563,
AUTHOR = "Wang, H.Y. and Qiang, C.Y. and Wang, T.R. and Gong, C. and Wang, L.B.",
TITLE = "Emotional Style Transfer With Intensity Control in Zero-Shot TTS",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3137-3141",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370666"}
@article{bb376564,
AUTHOR = "Cheong, S. and Kim, M. and Shin, J.W.",
TITLE = "Integrated DNN-Based Parameter Estimation for Multichannel Speech
Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3320-3324",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370667"}
@article{bb376565,
AUTHOR = "Jiang, W.B. and Wen, F. and Yu, K.",
TITLE = "MOS-GAN: Mean Opinion Score GAN for Unsupervised Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3465-3469",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370668"}
@article{bb376566,
AUTHOR = "Dmitrieva, E. and Kaledin, M.",
TITLE = "HiFi-Stream: Streaming Speech Enhancement With Generative Adversarial
Networks",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3595-3599",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370669"}
@article{bb376567,
AUTHOR = "Ma, W. and Zhu, Y.X. and Yang, J.",
TITLE = "Deep Preprocessing Method for Speech Restoration in Parametric Array
Loudspeakers via Time-Frequency Domain Modeling",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3720-3724",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370670"}
@article{bb376568,
AUTHOR = "Zhao, K. and Luo, X.Q. and Jin, J. and Jin, D. and Huang, G.P.",
TITLE = "Robust Fusion of Differential Beamformers for Speech Enhancement in
Dynamic Interference Conditions",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3794-3798",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370671"}
@article{bb376569,
AUTHOR = "Parisae, V. and Bhavanam, S.N.",
TITLE = "Stacked U-Net with Time-Frequency Attention and Deep Connection Net for
Single Channel Speech Enhancement",
JOURNAL = IJIG,
VOLUME = "26",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "2550067",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370672"}
@article{bb376570,
AUTHOR = "Wang, H. and Wang, C.L. and Wang, X.T. and Yu, L. and Jiang, Y.M.",
TITLE = "MBTU-SE: A Speech Enhancement Network Integrates Enhanced Taylor
Multi-Branch Linear Transformer With U-Net Architecture",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "4309-4313",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370673"}
@article{bb376571,
AUTHOR = "Pan, Y. and Yang, Y.G. and Yao, J. and Ma, L. and Zhao, J.J.",
TITLE = "Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and
Conditional Flow Matching",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "4199-4203",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370674"}
@article{bb376572,
AUTHOR = "Yu, J. and Park, H.",
TITLE = "Gradient-Aware Loss Function for Improved Learning in Speech
Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "763-767",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370675"}
@article{bb376573,
AUTHOR = "Kim, S.J. and Park, H.M.",
TITLE = "Beyond Noise Suppression: Dynamic Distortion Control Loss for Speech
Enhancement and Robust Automatic Speech Recognition",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "853-857",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370676"}
@article{bb376574,
AUTHOR = "Yang, S.Q. and Wu, J. and Lei, Y. and Tai, W.X. and Zhou, F.",
TITLE = "DOSE+: A Timestep-Aware Dropout Strategy for Diffusion Models in
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "858-862",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370677"}
@inproceedings{bb376575,
AUTHOR = "Wang, Q. and Song, X. and He, Y.H. and Han, J.Z. and Ding, C.H. and Gao, X.Y. and Gong, Y.H.",
TITLE = "Boosting Domain Incremental Learning: Selecting the Optimal
Parameters is All You Need",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4839-4849",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370678"}
@inproceedings{bb376576,
AUTHOR = "Li, X.S. and Tan, Z.H. and Xia, Z.C. and Wu, D. and Zhang, B.",
TITLE = "Single-Channel Speech Separation Focusing on Attention DE",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "3204-3209",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370679"}
@inproceedings{bb376577,
AUTHOR = "Xu, X.M. and Hao, J.J.",
TITLE = "U-Former: Improving Monaural Speech Enhancement with Multi-head Self
and Cross Attention",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "663-369",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370680"}
@inproceedings{bb376578,
AUTHOR = "Li, D.S. and Zhao, L.X. and Xiao, J. and Liu, J.Q. and Guan, D.Z. and Wang, Q.R.",
TITLE = "Adaptive Speech Intelligibility Enhancement for Far-and-Near-end Noise
Environments Based on Self-attention StarGAN",
BOOKTITLE = MMMod22,
YEAR = "2022",
PAGES = "II:205-217",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370681"}
@inproceedings{bb376579,
AUTHOR = "Xiao, J. and Liu, J.Q. and Li, D.S. and Zhao, L.X. and Wang, Q.R.",
TITLE = "Speech Intelligibility Enhancement By Non-Parallel Speech Style
Conversion Using CWT and iMetricGAN Based CycleGAN",
BOOKTITLE = MMMod22,
YEAR = "2022",
PAGES = "I:544-556",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370682"}
@inproceedings{bb376580,
AUTHOR = "Hegde, S.B. and Prajwal, K.R. and Mukhopadhyay, R. and Namboodiri, V. and Jawahar, C.V.",
TITLE = "Visual Speech Enhancement Without A Real Visual Stream",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "1925-1934",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370683"}
@inproceedings{bb376581,
AUTHOR = "Sun, Z.B. and Wang, Y.N. and Cao, L.",
TITLE = "An Attention Based Speaker-independent Audio-visual Deep Learning Model
for Speech Enhancement",
BOOKTITLE = MMMod20,
YEAR = "2020",
PAGES = "II:722-728",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370684"}
@inproceedings{bb376582,
AUTHOR = "Wang, Y.",
TITLE = "Research Progress in Speech Enhancement Technology",
BOOKTITLE = CVIDL20,
YEAR = "2020",
PAGES = "222-226",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370685"}
@inproceedings{bb376583,
AUTHOR = "Dendani, B. and Bahi, H. and Sari, T.",
TITLE = "Speech Enhancement Based on Deep Autoencoder for Remote Arabic Speech
Recognition",
BOOKTITLE = ICISP20,
YEAR = "2020",
PAGES = "221-229",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370686"}
@inproceedings{bb376584,
AUTHOR = "Coto Jimenez, M.",
TITLE = "Experimental Study on Transfer Learning in Denoising Autoencoders for
Speech Enhancement",
BOOKTITLE = MCPR20,
YEAR = "2020",
PAGES = "307-317",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370687"}
@inproceedings{bb376585,
AUTHOR = "Zhang, R. and Hu, R.M. and Li, G. and Wang, X.C.",
TITLE = "Spectral Tilt Estimation for Speech Intelligibility Enhancement Using
RNN Based on All-Pole Model",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "II:144-156",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370688"}
@inproceedings{bb376586,
AUTHOR = "Samui, S. and Chakrabarti, I. and Ghosh, S.K.",
TITLE = "Improving the Performance of Deep Learning Based Speech Enhancement
System Using Fuzzy Restricted Boltzmann Machine",
BOOKTITLE = PReMI17,
YEAR = "2017",
PAGES = "534-542",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370689"}
@inproceedings{bb376587,
AUTHOR = "Pignotti, A. and Marcozzi, D. and Cifani, S. and Squartini, S. and Piazza, F.",
TITLE = "A Blind Source Separation Based Approach for Speech Enhancement in
Noisy and Reverberant Environment",
BOOKTITLE = COST08,
YEAR = "2008",
PAGES = "356-367",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370690"}
@inproceedings{bb376588,
AUTHOR = "Kuhnapfel, T. and Tan, T. and Venkatesh, S. and Igel, B.",
TITLE = "Distributed Audio Network for Speech Enhancement in Challenging Noise
Backgrounds",
BOOKTITLE = AVSBS09,
YEAR = "2009",
PAGES = "308-313",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370691"}
@inproceedings{bb376589,
AUTHOR = "Kuhnapfel, T. and Tan, T. and Venkatesh, S. and Nordholm, S.E. and Igel, B.",
TITLE = "Adaptive speech enhancement with varying noise backgrounds",
BOOKTITLE = ICPR08,
YEAR = "2008",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370692"}
@inproceedings{bb376590,
AUTHOR = "Li, W.H. and Liu, M. and Zhu, Z.G. and Huang, T.S.",
TITLE = "LDV Remote Voice Acquisition and Enhancement",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "IV: 262-265",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT370693"}
@article{bb376591,
AUTHOR = "Yeh, C.Y. and Hwang, S.H.",
TITLE = "Efficient text analyser with prosody generator-driven approach for
Mandarin text-to-speech",
JOURNAL = VISP,
VOLUME = "152",
YEAR = "2005",
NUMBER = "6",
MONTH = "December",
PAGES = "793-799",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370694"}
@article{bb376592,
AUTHOR = "Chouireb, F. and Guerti, M.",
TITLE = "Towards a high quality Arabic speech synthesis system based on neural
networks and residual excited vocal tract model",
JOURNAL = SIViP,
VOLUME = "2",
YEAR = "2008",
NUMBER = "1",
MONTH = "January",
PAGES = "73-87",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370695"}
@article{bb376593,
AUTHOR = "Elfitri, I. and Gunel, B. and Kondoz, A.M.",
TITLE = "Multichannel Audio Coding Based on Analysis by Synthesis",
JOURNAL = PIEEE,
VOLUME = "99",
YEAR = "2011",
NUMBER = "4",
MONTH = "April",
PAGES = "657-670",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370696"}
@article{bb376594,
AUTHOR = "Jung, C.S. and Joo, Y.S. and Kang, H.G.",
TITLE = "Waveform Interpolation-Based Speech Analysis/Synthesis for HMM-Based
TTS Systems",
JOURNAL = SPLetters,
VOLUME = "19",
YEAR = "2012",
NUMBER = "12",
MONTH = "December",
PAGES = "809-812",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370697"}
@article{bb376595,
AUTHOR = "Carmona, J.L. and Barker, J. and Gomez, A.M. and Ma, N.",
TITLE = "Speech Spectral Envelope Enhancement by HMM-Based Analysis/Resynthesis",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "6",
PAGES = "563-566",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370698"}
@article{bb376596,
AUTHOR = "Tokuda, K. and Nankaku, Y. and Toda, T. and Zen, H. and Yamagishi, J. and Oura, K.",
TITLE = "Speech Synthesis Based on Hidden Markov Models",
JOURNAL = PIEEE,
VOLUME = "100",
YEAR = "2013",
NUMBER = "5",
MONTH = "May",
PAGES = "1234-1252",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370699"}
@article{bb376597,
AUTHOR = "Ling, Z. and Kang, S. and Zen, H. and Senior, A. and Schuster, M. and Qian, X. and Meng, H. and Deng, L.",
TITLE = "Deep Learning for Acoustic Modeling in Parametric Speech Generation:
A systematic review of existing techniques and future trends",
JOURNAL = SPMag,
VOLUME = "32",
YEAR = "2015",
NUMBER = "3",
MONTH = "May",
PAGES = "35-52",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370700"}
@article{bb376598,
AUTHOR = "Bordel, G. and Penagarikano, M. and Rodriguez Fuentes, L.J. and Alvarez, A. and Varona, A.",
TITLE = "Probabilistic Kernels for Improved Text-to-Speech Alignment in Long
Audio Tracks",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "1",
MONTH = "January",
PAGES = "126-129",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370701"}
@article{bb376599,
AUTHOR = "Ninh, D.K. and Yamashita, Y.",
TITLE = "F0 Parameterization of Glottalized Tones in HMM-Based Speech Synthesis
for Hanoi Vietnamese",
JOURNAL = IEICE,
VOLUME = "E98-D",
YEAR = "2015",
NUMBER = "12",
MONTH = "December",
PAGES = "2280-2289",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT370702"}
Last update:Feb 26, 2026 at 10:58:24