@article{bb388200,
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#TT382263"}
@article{bb388201,
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#TT382264"}
@article{bb388202,
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#TT382265"}
@article{bb388203,
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#TT382266"}
@article{bb388204,
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#TT382267"}
@article{bb388205,
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#TT382268"}
@article{bb388206,
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#TT382269"}
@article{bb388207,
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#TT382270"}
@article{bb388208,
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#TT382271"}
@article{bb388209,
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#TT382272"}
@article{bb388210,
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#TT382273"}
@article{bb388211,
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#TT382274"}
@article{bb388212,
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#TT382275"}
@article{bb388213,
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#TT382276"}
@article{bb388214,
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#TT382277"}
@article{bb388215,
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#TT382278"}
@article{bb388216,
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#TT382279"}
@article{bb388217,
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#TT382280"}
@article{bb388218,
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#TT382281"}
@article{bb388219,
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#TT382282"}
@article{bb388220,
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#TT382283"}
@article{bb388221,
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#TT382284"}
@article{bb388222,
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#TT382285"}
@article{bb388223,
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#TT382286"}
@article{bb388224,
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#TT382287"}
@article{bb388225,
AUTHOR = "Zhao, K. and Luo, X.Q. and Jin, J. and Jin, D.Q. 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#TT382288"}
@article{bb388226,
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#TT382289"}
@article{bb388227,
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#TT382290"}
@article{bb388228,
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#TT382291"}
@article{bb388229,
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#TT382292"}
@article{bb388230,
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#TT382293"}
@article{bb388231,
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#TT382294"}
@article{bb388232,
AUTHOR = "Gao, M.M. and Zhang, X.J. and Xiang, X.X.",
TITLE = "Real-World Speech Recovery Under Multiple Distortions: A Two-Stage
Framework With Feature Consistency and Adversarial Fine-Tuning",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "933-937",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382295"}
@article{bb388233,
AUTHOR = "Wang, Y.J. and Yang, X.R. and Huang, G.P.",
TITLE = "MCFLOW-SE: Efficient One-Step Multichannel Speech Enhancement via
Meanflow",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "1496-1500",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382296"}
@article{bb388234,
AUTHOR = "Liu, F. and Yang, S.Q. and Yang, G. and Tai, W.X. and Lei, Y. and Zhong, T. and Zhou, F.",
TITLE = "Diffusion for regression: A model-agnostic generative approach to
controllable speech enhancement",
JOURNAL = PRL,
VOLUME = "205",
YEAR = "2026",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382297"}
@article{bb388235,
AUTHOR = "Shen, X.Y. and Zhu, W.P. and Champagne, B.",
TITLE = "A Non-Learned Multi-Band Relative Contrastive Loss for Speech
Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "1916-1920",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382298"}
@article{bb388236,
AUTHOR = "Mukhutdinov, D. and Alex, A. and Cavallaro, A. and Wang, L.",
TITLE = "On the Consistency Between Subjective and Objective Evaluation for
Speech Enhancement Under Low-SNR Drone Noise",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2470-2474",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382299"}
@article{bb388237,
AUTHOR = "Li, T.Y. and Wang, H. and Yin, W. and Yan, Z. and Lv, H.",
TITLE = "CAR-STAM: Mamba-Based Speech Enhancement Combining Cyclic Asymmetric
Receptive Fields and Spatio-Temporal Coordinate Attention",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2545-2549",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382300"}
@article{bb388238,
AUTHOR = "Wang, H.F. and Gao, Y. and Guo, X. and Ou, S.F.",
TITLE = "TFMA-Net: A Time-Frequency Mamba Attention Network for Monaural
Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2660-2664",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382301"}
@article{bb388239,
AUTHOR = "Tao, L. and Jia, M. and Hu, Y.G.",
TITLE = "MulSE: Integrating Dual-Path Modeling and Global Attention for
Multi-Channel Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3014-3018",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382302"}
@article{bb388240,
AUTHOR = "Chakraborty, J. and Reed, M. and Thomos, N.",
TITLE = "S^3G-Net: Lightweight Banded Network for Real-Time Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2869-2873",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382303"}
@article{bb388241,
AUTHOR = "Zhang, J.M. and Li, H.Y. and Tewari, R.C. and Rao, W. and Razul, S.G. and Chng, E.S.",
TITLE = "TACE-Net: Two-Stage Asymmetric Conditional Enhancement for
Weak-Source Recovery in Co-Channel FM",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2904-2908",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382304"}
@article{bb388242,
AUTHOR = "Yang, L. and Wang, D. and Rong, X.B. and Zhao, J. and Lu, J.",
TITLE = "CoFi-Lite: Pushing the Limits of Ultra-Lightweight Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2954-2958",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382305"}
@article{bb388243,
AUTHOR = "Fang, M. and Zhu, Y.Y. and Li, Y.S. and Zhang, Q.Z.",
TITLE = "Synergistic Quantization for Generalized Cauchy Adaptive Filters in
Acoustic Echo Cancellation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2959-2963",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382306"}
@article{bb388244,
AUTHOR = "Xu, S. and Cao, Y.H. and He, C.J. and Zhang, W.J. and Wang, M.J.",
TITLE = "ADS-BiMamba: Attentive Dynamic-Split Bidirectional Mamba for
Multi-Channel Speech Enhancement",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3242-3246",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382307"}
@article{bb388245,
AUTHOR = "Fan, C.H. and Liu, E. and Zhou, J. and Kang, J. and Li, J. and Li, A.D. and Zhou, J. and Lv, Z. and Li, X.",
TITLE = "DBHN-Net: Dual-Branch Hybrid Neural Network for Low-Complexity
Monaural Speech Enhancement",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "10",
MONTH = "October",
PAGES = "12196-12210",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382308"}
@article{bb388246,
AUTHOR = "Sun, H.H. and Ai, Y. and Du, H.P. and Ling, Z.H. and Guo, W.",
TITLE = "Multichannel Speech Enhancement With Spatial-Aware Explicit Phase
Estimation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3496-3500",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382309"}
@article{bb388247,
AUTHOR = "Liang, H. and Liu, W. and Huang, G.P. and Makino, S.",
TITLE = "EquilSE: Time-Invariant Generative Speech Enhancement via Equilibrium
Matching",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3581-3585",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382310"}
@article{bb388248,
AUTHOR = "Zhao, Z. and Li, J. and Li, S.Q. and Xu, Z.Y.",
TITLE = "Subnetwork-Specific Distributed Speech Enhancement for Multiple
Sources Using Acoustic Sensor Networks",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3716-3720",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024spen2.html#TT382311"}
@inproceedings{bb388249,
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#TT382312"}
@inproceedings{bb388250,
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#TT382313"}
@inproceedings{bb388251,
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#TT382314"}
@inproceedings{bb388252,
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#TT382315"}
@inproceedings{bb388253,
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#TT382316"}
@inproceedings{bb388254,
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#TT382317"}
@inproceedings{bb388255,
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#TT382318"}
@inproceedings{bb388256,
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#TT382319"}
@inproceedings{bb388257,
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#TT382320"}
@inproceedings{bb388258,
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#TT382321"}
@inproceedings{bb388259,
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#TT382322"}
@inproceedings{bb388260,
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#TT382323"}
@inproceedings{bb388261,
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#TT382324"}
@inproceedings{bb388262,
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#TT382325"}
@inproceedings{bb388263,
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#TT382326"}
@inproceedings{bb388264,
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#TT382327"}
@article{bb388265,
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#TT382328"}
@article{bb388266,
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#TT382329"}
@article{bb388267,
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#TT382330"}
@article{bb388268,
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#TT382331"}
@article{bb388269,
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#TT382332"}
@article{bb388270,
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#TT382333"}
@article{bb388271,
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#TT382334"}
@article{bb388272,
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#TT382335"}
@article{bb388273,
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#TT382336"}
@article{bb388274,
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#TT382337"}
@article{bb388275,
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#TT382338"}
@article{bb388276,
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#TT382339"}
@article{bb388277,
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#TT382340"}
@article{bb388278,
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#TT382341"}
@article{bb388279,
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#TT382342"}
@article{bb388280,
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#TT382343"}
@article{bb388281,
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#TT382344"}
@article{bb388282,
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#TT382345"}
@article{bb388283,
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#TT382346"}
@article{bb388284,
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#TT382347"}
@article{bb388285,
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#TT382348"}
@article{bb388286,
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#TT382349"}
@article{bb388287,
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#TT382350"}
@article{bb388288,
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#TT382351"}
@article{bb388289,
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#TT382352"}
@article{bb388290,
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#TT382353"}
@article{bb388291,
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#TT382354"}
@article{bb388292,
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#TT382355"}
@article{bb388293,
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#TT382356"}
@article{bb388294,
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#TT382357"}
@article{bb388295,
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#TT382358"}
@article{bb388296,
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#TT382359"}
@article{bb388297,
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#TT382360"}
@article{bb388298,
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#TT382361"}
@article{bb388299,
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#TT382362"}
Last update:Sep 30, 2026 at 11:45:00