@article{bb368200,
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#TT362365"}
@article{bb368201,
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#TT362366"}
@article{bb368202,
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#TT362367"}
@article{bb368203,
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#TT362368"}
@article{bb368204,
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#TT362369"}
@article{bb368205,
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#TT362370"}
@article{bb368206,
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#TT362371"}
@article{bb368207,
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#TT362372"}
@article{bb368208,
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#TT362373"}
@article{bb368209,
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#TT362374"}
@article{bb368210,
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#TT362375"}
@article{bb368211,
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#TT362376"}
@article{bb368212,
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#TT362377"}
@article{bb368213,
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#TT362378"}
@article{bb368214,
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#TT362379"}
@article{bb368215,
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#TT362380"}
@article{bb368216,
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#TT362381"}
@article{bb368217,
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#TT362382"}
@article{bb368218,
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#TT362383"}
@article{bb368219,
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#TT362384"}
@article{bb368220,
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#TT362385"}
@article{bb368221,
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#TT362386"}
@article{bb368222,
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#TT362387"}
@article{bb368223,
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#TT362388"}
@article{bb368224,
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#TT362389"}
@article{bb368225,
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#TT362390"}
@article{bb368226,
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#TT362391"}
@article{bb368227,
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#TT362392"}
@article{bb368228,
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#TT362393"}
@article{bb368229,
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#TT362394"}
@article{bb368230,
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#TT362395"}
@article{bb368231,
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#TT362396"}
@article{bb368232,
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#TT362397"}
@article{bb368233,
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#TT362398"}
@article{bb368234,
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#TT362399"}
@article{bb368235,
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#TT362400"}
@article{bb368236,
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#TT362401"}
@article{bb368237,
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#TT362402"}
@article{bb368238,
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#TT362403"}
@article{bb368239,
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#TT362404"}
@article{bb368240,
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#TT362405"}
@article{bb368241,
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#TT362406"}
@article{bb368242,
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#TT362407"}
@article{bb368243,
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#TT362408"}
@article{bb368244,
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#TT362409"}
@article{bb368245,
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#TT362410"}
@article{bb368246,
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#TT362411"}
@article{bb368247,
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#TT362412"}
@article{bb368248,
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#TT362413"}
@inproceedings{bb368249,
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#TT362414"}
@inproceedings{bb368250,
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#TT362415"}
@inproceedings{bb368251,
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#TT362416"}
@inproceedings{bb368252,
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#TT362417"}
@inproceedings{bb368253,
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#TT362418"}
@inproceedings{bb368254,
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#TT362419"}
@inproceedings{bb368255,
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#TT362420"}
@inproceedings{bb368256,
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#TT362421"}
@inproceedings{bb368257,
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#TT362422"}
@inproceedings{bb368258,
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#TT362423"}
@inproceedings{bb368259,
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#TT362424"}
@inproceedings{bb368260,
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#TT362425"}
@inproceedings{bb368261,
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#TT362426"}
@inproceedings{bb368262,
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#TT362427"}
@inproceedings{bb368263,
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#TT362428"}
@inproceedings{bb368264,
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#TT362429"}
@article{bb368265,
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#TT362430"}
@article{bb368266,
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#TT362431"}
@article{bb368267,
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#TT362432"}
@article{bb368268,
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#TT362433"}
@article{bb368269,
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#TT362434"}
@article{bb368270,
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#TT362435"}
@article{bb368271,
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#TT362436"}
@article{bb368272,
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#TT362437"}
@article{bb368273,
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#TT362438"}
@article{bb368274,
AUTHOR = "Erro, D.",
TITLE = "Two-Band Radial Postfiltering in Cepstral Domain with Application to
Speech Synthesis",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "2",
MONTH = "February",
PAGES = "202-206",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362439"}
@article{bb368275,
AUTHOR = "Hu, Y.J. and Ling, Z.H.",
TITLE = "DBN-based Spectral Feature Representation for Statistical Parametric
Speech Synthesis",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "3",
MONTH = "March",
PAGES = "321-325",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362440"}
@article{bb368276,
AUTHOR = "Tsiaras, V. and Maia, R. and Diakoloukas, V. and Stylianou, Y. and Digalakis, V.",
TITLE = "Global Variance in Speech Synthesis With Linear Dynamical Models",
JOURNAL = SPLetters,
VOLUME = "23",
YEAR = "2016",
NUMBER = "8",
MONTH = "August",
PAGES = "1057-1061",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362441"}
@article{bb368277,
AUTHOR = "Wang, F.Z. and Nagano, H. and Kashino, K. and Igarashi, T.",
TITLE = "Visualizing Video Sounds With Sound Word Animation to Enrich User
Experience",
JOURNAL = MultMed,
VOLUME = "19",
YEAR = "2017",
NUMBER = "2",
MONTH = "February",
PAGES = "418-429",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362442"}
@article{bb368278,
AUTHOR = "Sharma, B. and Prasanna, S.R.M.",
TITLE = "Enhancement of Spectral Tilt in Synthesized Speech",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "4",
MONTH = "April",
PAGES = "382-386",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362443"}
@article{bb368279,
AUTHOR = "Singh, R. and Jimenez, A. and Oland, A.",
TITLE = "Voice disguise by mimicry: deriving statistical articulometric evidence
to evaluate claimed impersonation",
JOURNAL = IET-Bio,
VOLUME = "6",
YEAR = "2017",
NUMBER = "4",
MONTH = "July",
PAGES = "282-289",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362444"}
@article{bb368280,
AUTHOR = "Lee, K.S.",
TITLE = "Restricted Boltzmann Machine-Based Voice Conversion for Nonparallel
Corpus",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "8",
MONTH = "August",
PAGES = "1103-1107",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362445"}
@article{bb368281,
AUTHOR = "Reddy, M.K. and Rao, K.S.",
TITLE = "Robust Pitch Extraction Method for the HMM-Based Speech Synthesis
System",
JOURNAL = SPLetters,
VOLUME = "24",
YEAR = "2017",
NUMBER = "8",
MONTH = "August",
PAGES = "1133-1137",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362446"}
@article{bb368282,
AUTHOR = "Liu, Z.C. and Ling, Z.H. and Dai, L.R.",
TITLE = "Statistical Parametric Speech Synthesis Using Generalized
Distillation Framework",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "5",
MONTH = "May",
PAGES = "695-699",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362447"}
@article{bb368283,
AUTHOR = "Drugman, T. and Huybrechts, G. and Klimkov, V. and Moinet, A.",
TITLE = "Traditional Machine Learning for Pitch Detection",
JOURNAL = SPLetters,
VOLUME = "25",
YEAR = "2018",
NUMBER = "11",
MONTH = "November",
PAGES = "1745-1749",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362448"}
@article{bb368284,
AUTHOR = "Arik, S.O. and Jun, H. and Diamos, G.",
TITLE = "Fast Spectrogram Inversion Using Multi-Head Convolutional Neural
Networks",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "1",
MONTH = "January",
PAGES = "94-98",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362449"}
@article{bb368285,
AUTHOR = "Masuyama, Y. and Yatabe, K. and Oikawa, Y.",
TITLE = "Griffin-Lim Like Phase Recovery via Alternating Direction Method of
Multipliers",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "1",
MONTH = "January",
PAGES = "184-188",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362450"}
@article{bb368286,
AUTHOR = "Kwon, O. and Jang, I. and Ahn, C. and Kang, H.",
TITLE = "An Effective Style Token Weight Control Technique for End-to-End
Emotional Speech Synthesis",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "9",
MONTH = "September",
PAGES = "1383-1387",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362451"}
@article{bb368287,
AUTHOR = "Liu, Q. and Jackson, P.J.B. and Wang, W.",
TITLE = "A Speech Synthesis Approach for High Quality Speech Separation and
Generation",
JOURNAL = SPLetters,
VOLUME = "26",
YEAR = "2019",
NUMBER = "12",
MONTH = "December",
PAGES = "1872-1876",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362452"}
@article{bb368288,
AUTHOR = "Cotescu, M. and Drugman, T. and Huybrechts, G. and Lorenzo Trueba, J. and Moinet, A.",
TITLE = "Voice Conversion for Whispered Speech Synthesis",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "186-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362453"}
@article{bb368289,
AUTHOR = "Aylett, M.P. and Vinciarelli, A. and Wester, M.",
TITLE = "Speech Synthesis for the Generation of Artificial Personality",
JOURNAL = AffCom,
VOLUME = "11",
YEAR = "2020",
NUMBER = "2",
MONTH = "April",
PAGES = "361-372",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362454"}
@article{bb368290,
AUTHOR = "Rao, M.V.A. and Ghosh, P.K.",
TITLE = "SFNet: A Computationally Efficient Source Filter Model Based Neural
Speech Synthesis",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1170-1174",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362455"}
@article{bb368291,
AUTHOR = "Zhou, Y. and Tian, X. and Li, H.",
TITLE = "Multi-Task WaveRNN With an Integrated Architecture for Cross-Lingual
Voice Conversion",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1310-1314",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362456"}
@article{bb368292,
AUTHOR = "Yang, J.C. and Lin, P. and He, Q.H.",
TITLE = "Constant-Q magnitude-phase coefficients extraction for synthetic speech
detection",
JOURNAL = IET-Bio,
VOLUME = "9",
YEAR = "2020",
NUMBER = "5",
MONTH = "September",
PAGES = "216-221",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362457"}
@article{bb368293,
AUTHOR = "Liu, R. and Sisman, B. and Bao, F. and Gao, G. and Li, H.",
TITLE = "Modeling Prosodic Phrasing With Multi-Task Learning in Tacotron-Based
TTS",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1470-1474",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362458"}
@article{bb368294,
AUTHOR = "Qi, J. and Du, J. and Siniscalchi, S.M. and Ma, X. and Lee, C.",
TITLE = "On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector
Regression",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1485-1489",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362459"}
@article{bb368295,
AUTHOR = "Yang, S. and Wang, Y. and Xie, L.",
TITLE = "Adversarial Feature Learning and Unsupervised Clustering Based Speech
Synthesis for Found Data With Acoustic and Textual Noise",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "1730-1734",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362460"}
@article{bb368296,
AUTHOR = "Lee, J.Y. and Cheon, S.J. and Choi, B.J. and Kim, N.S.",
TITLE = "Memory Attention: Robust Alignment Using Gating Mechanism for
End-to-End Speech Synthesis",
JOURNAL = SPLetters,
VOLUME = "27",
YEAR = "2020",
PAGES = "2004-2008",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362461"}
@article{bb368297,
AUTHOR = "Zhang, Y. and Jiang, F. and Duan, Z.Y.",
TITLE = "One-Class Learning Towards Synthetic Voice Spoofing Detection",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "937-941",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362462"}
@article{bb368298,
AUTHOR = "Saeki, T. and Takamichi, S. and Saruwatari, H.",
TITLE = "Incremental Text-to-Speech Synthesis Using Pseudo Lookahead With
Large Pretrained Language Model",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "857-861",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362463"}
@article{bb368299,
AUTHOR = "Comanducci, L. and Bestagini, P. and Tagliasacchi, M. and Sarti, A. and Tubaro, S.",
TITLE = "Reconstructing Speech From CNN Embeddings",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "952-956",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT362464"}
Last update:Oct 6, 2025 at 14:07:43