@article{bb374300,
AUTHOR = "Zhou, Y. and Wu, Z.Z. and Zhang, M.Y. and Tian, X.H. and Li, H.Z.",
TITLE = "TTS-Guided Training for Accent Conversion Without Parallel Data",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "533-537",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368404"}
@article{bb374301,
AUTHOR = "Koepke, A.S. and Oncescu, A.M. and Henriques, J.F. and Akata, Z. and Albanie, S.",
TITLE = "Audio Retrieval With Natural Language Queries: A Benchmark Study",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "2675-2685",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368405"}
@article{bb374302,
AUTHOR = "Park, D. and Yu, Y. and Katabi, D. and Kim, H.K.",
TITLE = "Adversarial Continual Learning to Transfer Self-Supervised Speech
Representations for Voice Pathology Detection",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "932-936",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368406"}
@article{bb374303,
AUTHOR = "Kim, H. and Shin, J.W.",
TITLE = "On Training Speech Separation Models With Various Numbers of Speakers",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1202-1206",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368407"}
@article{bb374304,
AUTHOR = "Joglekar, A. and Hansen, J.H.L.",
TITLE = "DeepComboSAD: Spectro-Temporal Correlation Based Speech Activity
Detection for Naturalistic Audio Streams",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1472-1476",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368408"}
@article{bb374305,
AUTHOR = "Cai, Y.Q. and Li, L. and Abel, A. and Zhu, X.Y. and Wang, D.",
TITLE = "Maximum Gaussianality training for deep speaker vector normalization",
JOURNAL = PR,
VOLUME = "145",
YEAR = "2024",
PAGES = "109977",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368409"}
@article{bb374306,
AUTHOR = "Raman, C. and Prabhu, N.R. and Hung, H.",
TITLE = "Perceived Conversation Quality in Spontaneous Interactions",
JOURNAL = AffCom,
VOLUME = "14",
YEAR = "2023",
NUMBER = "4",
MONTH = "October",
PAGES = "2901-2912",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368410"}
@inproceedings{bb374307,
AUTHOR = "Atito, S. and Awais, M. and Alex, T. and Kittler, J.V.",
TITLE = "Group Masked Model Learning for General Audio Representation",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2600-2604",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368411"}
@article{bb374308,
AUTHOR = "Lee, H. and Saeed, A.",
TITLE = "Distilled non-semantic speech embeddings with binary neural networks
for low-resource devices",
JOURNAL = PRL,
VOLUME = "177",
YEAR = "2024",
PAGES = "15-19",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368412"}
@article{bb374309,
AUTHOR = "Ye, L.X. and Gao, C.F. and Cheng, G.F. and Luo, L.P. and Zhao, Q.W.",
TITLE = "ASQ: An Ultra-Low Bit Rate ASR-Oriented Speech Quantization Method",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "221-225",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368413"}
@article{bb374310,
AUTHOR = "Li, C.T. and Yang, F. and Yang, J.",
TITLE = "Restoration of Bone-Conducted Speech With U-Net-Like Model and Energy
Distance Loss",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "166-170",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368414"}
@article{bb374311,
AUTHOR = "Rababaah, A.R.",
TITLE = "Intelligent classification model for holy Quran recitation Maqams",
JOURNAL = IJCVR,
VOLUME = "14",
YEAR = "2024",
NUMBER = "2",
PAGES = "170-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368415"}
@article{bb374312,
AUTHOR = "Muraleedharan, K.M. and Kumar, K.T.B. and John, S.I. and Kumar, R.K. .S.I.",
TITLE = "Combined Use of Nonlinear Measures for Analyzing Pathological Voices",
JOURNAL = IJIG,
VOLUME = "24",
YEAR = "2024",
NUMBER = "3",
MONTH = "May",
PAGES = "2450035",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368416"}
@article{bb374313,
AUTHOR = "Wang, Z.Q.",
TITLE = "Mixture to Mixture: Leveraging Close-Talk Mixtures as
Weak-Supervision for Speech Separation",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1715-1719",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368417"}
@article{bb374314,
AUTHOR = "Zhang, C. and Jiang, S.",
TITLE = "Detection of QIM-Based Steganography in VoIP Streams:
A MobileViT-Inspired Model",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1735-1739",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368418"}
@article{bb374315,
AUTHOR = "Wang, Z.C. and Chen, Y.Z. and Wang, X.S. and Xie, L. and Wang, Y.P.",
TITLE = "StreamVoice+: Evolving Into End-to-End Streaming Zero-Shot Voice
Conversion",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "3000-3004",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368419"}
@article{bb374316,
AUTHOR = "Guo, N. and Edler, B.",
TITLE = "Frequency Domain Prediction of Tonal Signals With Time-Varying
Pitches",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "31-35",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368420"}
@article{bb374317,
AUTHOR = "Lopez Espejo, I. and Rosello, E. and Edraki, A. and Harte, N. and Jensen, J.",
TITLE = "Noise-Robust Hearing Aid Voice Control",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "241-245",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368421"}
@article{bb374318,
AUTHOR = "Xie, H. and Khorrami, K. and Rasanen, O. and Virtanen, T.",
TITLE = "Text-Based Audio Retrieval by Learning From Similarities Between
Audio Captions",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "221-225",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368422"}
@article{bb374319,
AUTHOR = "Yuan, C.S. and Chen, Y.F. and Zhou, Z. and Xia, Z.H. and Huang, Y.F.",
TITLE = "Compressed Domain Invariant Adversarial Representation Learning for
Robust Audio Deepfake Detection",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1111-1115",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368423"}
@article{bb374320,
AUTHOR = "Unoki, M. and Li, K. and Chaiwongyen, A. and Nguyen, Q.H. and Zaman, K.",
TITLE = "Deepfake Speech Detection: Approaches from Acoustic Features to Deep
Neural Networks",
JOURNAL = IEICE,
VOLUME = "E108-D",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "300-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368424"}
@article{bb374321,
AUTHOR = "Shin, U.H. and Ku, B.H. and Park, H.M.",
TITLE = "TF-CorrNet: Leveraging Spatial Correlation for Continuous Speech
Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1875-1879",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368425"}
@article{bb374322,
AUTHOR = "Ta, B.T. and Le, N.M. and Binh, H.T.T. and Do, V.H.",
TITLE = "Exploring Non-Matching Multiple References for Speech Quality
Assessment",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1610-1614",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368426"}
@article{bb374323,
AUTHOR = "Jin, L.B. and Min, D. and Yu, C. and Shin, J.E. and Kim, E.Y.",
TITLE = "Detecting Hearing Impairment Through Localizing Abnormal Speech
Patterns",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1945-1949",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368427"}
@article{bb374324,
AUTHOR = "Liu, D. and Zhang, T.Q. and Wei, Y. and Yi, C. and Christensen, M.G.",
TITLE = "Speech Conv-Mamba: Selective Structured State Space Model With
Temporal Dilated Convolution for Efficient Speech Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2015-2019",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368428"}
@article{bb374325,
AUTHOR = "Liu, F. and Ai, Y. and Ling, Z.H.",
TITLE = "Token-Prediction-Based Post-Processing for Low-Bitrate Speech Coding",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3235-3239",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368429"}
@article{bb374326,
AUTHOR = "Zhang, Z.X. and Xu, W.X. and Dong, Z. and Wang, K.L. and Wu, Y.M. and Peng, J. and Wang, R. and Huang, D.Y.",
TITLE = "ParaLBench: A Large-Scale Benchmark for Computational Paralinguistics
Over Acoustic Foundation Models",
JOURNAL = AffCom,
VOLUME = "16",
YEAR = "2025",
NUMBER = "3",
MONTH = "July",
PAGES = "1290-1306",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368430"}
@article{bb374327,
AUTHOR = "Yang, Y. and Zhou, C.",
TITLE = "DPARNet-RSE: Toward Angular Region-Customizable Speech Extraction",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3779-3783",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368431"}
@article{bb374328,
AUTHOR = "Zhao, Z.Y. and Peng, Y. and Camilleri, K. and Kong, W.Z. and Cichocki, A.",
TITLE = "Imagined Speech Decoding by Learning Consensus Graph From RKHS-Based
Multi-View EEG Features",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3944-3948",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368432"}
@article{bb374329,
AUTHOR = "Tan, Z.W. and Reju, V.G. and Tewari, R.C. and Ding, R.T. and Khong, A.W.H.",
TITLE = "Joint Enhancement and Bandwidth Extension for Radar Through-Barrier
Speech Acquisition",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "176-180",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368433"}
@inproceedings{bb374330,
AUTHOR = "Wani, T.M. and Amerini, I.",
TITLE = "Deepfakes Audio Detection Leveraging Audio Spectrogram and
Convolutional Neural Networks",
BOOKTITLE = CIAP23,
YEAR = "2023",
PAGES = "II:156-167",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368434"}
@inproceedings{bb374331,
AUTHOR = "Choi, S. and Oh, S. and Yang, J. and Lee, Y. and Kwak, I.Y.",
TITLE = "Light-weight Frequency Information Aware Neural Network Architecture
for Voice Spoofing Detection",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "477-483",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368435"}
@inproceedings{bb374332,
AUTHOR = "Li, X. and Hu, X. and Chen, X. and Pan, H. and Niu, K.",
TITLE = "Deep Speaker Embedding Using Hybrid Network of Multi-Feature
Aggregation and Multi-Loss Fusion for TI-SV",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "506-512",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368436"}
@inproceedings{bb374333,
AUTHOR = "Zhang, B. and Sim, T.",
TITLE = "Localizing Fake Segments in Speech",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "3224-3230",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368437"}
@inproceedings{bb374334,
AUTHOR = "Teng, Z.W. and Fu, Q. and White, J. and Powell, M.E. and Schmidt, D.C.",
TITLE = "ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof
Speech Detection",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "692-698",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368438"}
@inproceedings{bb374335,
AUTHOR = "Stefanov, K. and Adiban, M. and Salvi, G.",
TITLE = "Spatial Bias in Vision-Based Voice Activity Detection",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "10433-10440",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368439"}
@inproceedings{bb374336,
AUTHOR = "Barros, F. and Conde, A. and Soares, S.C. and Neves, A.J.R. and Silva, S.",
TITLE = "Understanding Public Speakers' Performance:
First Contributions to Support a Computational Approach",
BOOKTITLE = ICIAR20,
YEAR = "2020",
PAGES = "I:343-355",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368440"}
@inproceedings{bb374337,
AUTHOR = "Bilkova, Z. and Novozamsky, A. and Dominec, A. and Gresko, S. and Zitova, B. and Paroubkova, M.",
TITLE = "Automatic Evaluation of Speech Therapy Exercises Based on Image Data",
BOOKTITLE = ICIAR19,
YEAR = "2019",
PAGES = "I:397-404",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368441"}
@inproceedings{bb374338,
AUTHOR = "Dai, J.J. and Dixon, S.",
TITLE = "Understanding Intonation Trajectories and Patterns of Vocal Notes",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "II:243-253",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368442"}
@inproceedings{bb374339,
AUTHOR = "Zheng, S. and Wang, J. and Xiao, J. and Hsu, W. and Glass, J.",
TITLE = "A Noise-Robust Self-Adaptive Multitarget Speaker Detection System",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "1068-1072",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368443"}
@inproceedings{bb374340,
AUTHOR = "Athanasopoulos, G. and Hagihara, K. and Cierro, A. and Guerit, R. and Chatelain, J. and Lucas, C. and Macq, B.",
TITLE = "3D immersive karaoke for the learning of foreign language
pronunciation",
BOOKTITLE = IC3D17,
YEAR = "2017",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368444"}
@inproceedings{bb374341,
AUTHOR = "Serras, M. and Torres, M.I. and del Pozo, A.",
TITLE = "Online Learning of Attributed Bi-Automata for Dialogue Management in
Spoken Dialogue Systems",
BOOKTITLE = IbPRIA17,
YEAR = "2017",
PAGES = "22-31",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368445"}
@inproceedings{bb374342,
AUTHOR = "Nagpal, A. and Patil, H.A.",
TITLE = "Novel Gammatone Filterbank Based Spectro-Temporal Features for Robust
Phoneme Recognition",
BOOKTITLE = PReMI17,
YEAR = "2017",
PAGES = "342-350",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368446"}
@inproceedings{bb374343,
AUTHOR = "Grachev, A.M. and Ignatov, D.I. and Savchenko, A.V.",
TITLE = "Neural Networks Compression for Language Modeling",
BOOKTITLE = PReMI17,
YEAR = "2017",
PAGES = "351-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368447"}
@inproceedings{bb374344,
AUTHOR = "Zhang, L. and Chen, J.X. and Luo, Y. and Fu, J.F. and Ye, Z.F.",
TITLE = "Supervised single-channel speech dereverberation and denoising using
a two-stage processing",
BOOKTITLE = ICIVC17,
YEAR = "2017",
PAGES = "818-822",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368448"}
@inproceedings{bb374345,
AUTHOR = "Bedoui, A. and Ben Jebara, S.",
TITLE = "On the use of opening phase slopes of the glottal signal to
characterize unilateral vocal folds paralysis",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "41-46",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368449"}
@inproceedings{bb374346,
AUTHOR = "Ben Ali, F. and Djaziri Larbi, S.",
TITLE = "A very low bit rate codec for wide band speech based on a long-term
perceptual harmonic plus noise model",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "71-76",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368450"}
@inproceedings{bb374347,
AUTHOR = "Ferreira, A.",
TITLE = "Implantation of voicing on whispered speech using frequency-domain
parametric modelling of source and filter information",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "159-166",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368451"}
@inproceedings{bb374348,
AUTHOR = "Pozzebon, A. and Biliotti, F. and Calamai, S.",
TITLE = "Places Speaking with Their Own Voices. A Case Study from the Gra.fo
Archives",
BOOKTITLE = EuroMed16,
YEAR = "2016",
PAGES = "II: 232-239",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368452"}
@inproceedings{bb374349,
AUTHOR = "Vlaj, D. and Kos, M. and Kacic, Z.",
TITLE = "Quick and efficient definition of hangbefore and hangover criteria
for voice activity detection",
BOOKTITLE = WSSIP16,
YEAR = "2016",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368453"}
@inproceedings{bb374350,
AUTHOR = "Ballesteros L, D.M. and Renza, D. and Camacho, S.",
TITLE = "High Scrambling Degree in Audio Through Imitation of an Unintelligible
Signal",
BOOKTITLE = MCPR16,
YEAR = "2016",
PAGES = "251-259",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368454"}
@inproceedings{bb374351,
AUTHOR = "Onchis, D.M. and Real, P.",
TITLE = "On Homotopy Continuation for Speech Restoration",
BOOKTITLE = CTIC16,
YEAR = "2016",
PAGES = "152-156",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368455"}
@inproceedings{bb374352,
AUTHOR = "Dubey, M.L. and Shultz, P.F. and Kenyon, G.T.",
TITLE = "Learning phase-rich features from streaming auditory images",
BOOKTITLE = Southwest16,
YEAR = "2016",
PAGES = "73-76",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368456"}
@inproceedings{bb374353,
AUTHOR = "Montalvo, A. and Costa, Y.M.G. and Calvo, J.R.",
TITLE = "Language Identification Using Spectrogram Texture",
BOOKTITLE = CIARP15,
YEAR = "2015",
PAGES = "543-550",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368457"}
@inproceedings{bb374354,
AUTHOR = "Aizezi, Y. and Jamal, A. and Mamat, D. and Abdurexit, R. and Ubul, K.",
TITLE = "Analytical Method and Research of Uyghur Language Chunks Based on
Digital Forensics",
BOOKTITLE = ISCA15,
YEAR = "2015",
PAGES = "258-266",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368458"}
@inproceedings{bb374355,
AUTHOR = "Hammami, N. and Bedda, M. and Farah, N. and Mansouri, S.",
TITLE = "R-Letter disorder diagnosis (R-LDD): Arabic speech database
development for automatic diagnosis of childhood speech disorders
(Case study)",
BOOKTITLE = ISCV15,
YEAR = "2015",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368459"}
@inproceedings{bb374356,
AUTHOR = "Nakajima, J. and Kimura, A. and Sugimoto, A. and Kashino, K.",
TITLE = "Visual Attention Driven by Auditory Cues",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "II: 74-86",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368460"}
@inproceedings{bb374357,
AUTHOR = "Ishikura, K. and Uemura, A. and Katto, J.",
TITLE = "Live Version Identification with Audio Scene Detection",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 408-417",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368461"}
@inproceedings{bb374358,
AUTHOR = "Xie, S.B. and Yang, Y.H. and Hu, R.M. and Wang, Y.Y. and Yu, H.J. and Dong, S.L. and Gao, L. and Yang, C.",
TITLE = "Signal-Aware Parametric Quality Model for Audio and Speech over IP
Networks",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 487-497",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368462"}
@inproceedings{bb374359,
AUTHOR = "Xue, L. and Su, F.",
TITLE = "Auditory Scene Classification with Deep Belief Network",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 348-359",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368463"}
@inproceedings{bb374360,
AUTHOR = "Tu, M. and Xie, X. and Na, X.Y.",
TITLE = "Computational Auditory Scene Analysis Based Voice Activity Detection",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "797-802",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368464"}
@inproceedings{bb374361,
AUTHOR = "Lu, T. and Weng, Y.B. and Wang, G.Y.",
TITLE = "Audiotory Movie Summarization by Detecting Scene Changes and Sound
Events",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "756-760",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368465"}
@inproceedings{bb374362,
AUTHOR = "Nguyen Son, H.Q. and Hoang, A.T. and Tran, M.T. and Yoshiura, H. and Sonehara, N. and Echizen, I.",
TITLE = "Anonymizing Temporal Phrases in Natural Language Text to be Posted on
Social Networking Services",
BOOKTITLE = IWDW13,
YEAR = "2013",
PAGES = "437-451",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368466"}
@inproceedings{bb374363,
AUTHOR = "Maka, T. and Dziurzanski, P.",
TITLE = "Feature contours fusion for determining segment boundaries in audio
data",
BOOKTITLE = WSSIP14,
YEAR = "2014",
PAGES = "111-114",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368467"}
@inproceedings{bb374364,
AUTHOR = "Souza, D. and Saturnino, L. and Maciel, A.M.A.",
TITLE = "A portability evaluation of Brazilian Portuguese voices produced with
MARY TTS",
BOOKTITLE = WSSIP14,
YEAR = "2014",
PAGES = "95-98",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368468"}
@inproceedings{bb374365,
AUTHOR = "Frid, A. and Lavner, Y.Z.",
TITLE = "Spectral and textural features for automatic classification of
fricatives using SVM",
BOOKTITLE = WSSIP14,
YEAR = "2014",
PAGES = "99-102",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368469"}
@inproceedings{bb374366,
AUTHOR = "Savchenko, A.V.",
TITLE = "Semi-automated Speaker Adaptation:
How to Control the Quality of Adaptation?",
BOOKTITLE = ICISP14,
YEAR = "2014",
PAGES = "638-646",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368470"}
@inproceedings{bb374367,
AUTHOR = "Merazka, F.",
TITLE = "Wideband Speech Encryption Based Arnold Cat Map for AMR-WB G.722.2
Codec",
BOOKTITLE = ICISP14,
YEAR = "2014",
PAGES = "658-664",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368471"}
@inproceedings{bb374368,
AUTHOR = "Souli, S. and Lachiri, Z. and Kuznietsov, A.",
TITLE = "Using Three Reassigned Spectrogram Patches and Log-Gabor Filter for
Audio Surveillance Application",
BOOKTITLE = CIARP13,
YEAR = "2013",
PAGES = "I:527-534",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368472"}
@inproceedings{bb374369,
AUTHOR = "Joseph, S.M. and Babu, A.P.",
TITLE = "Continuous speech coding using coiflets wavelet",
BOOKTITLE = ICSIPR13,
YEAR = "2013",
PAGES = "253-257",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368473"}
@inproceedings{bb374370,
AUTHOR = "Nivedita, D. and Kavita, T. and Zadgaonkar, A.S.",
TITLE = "First degree heart block determination from speech analysis",
BOOKTITLE = ICSIPR13,
YEAR = "2013",
PAGES = "103-106",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368474"}
@article{bb374371,
AUTHOR = "Sadjadi, S.O. and Hansen, J.H.L.",
TITLE = "Unsupervised Speech Activity Detection Using Voicing Measures and
Perceptual Spectral Flux",
JOURNAL = SPLetters,
VOLUME = "20",
YEAR = "2013",
NUMBER = "3",
MONTH = "March",
PAGES = "197-200",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368475"}
@inproceedings{bb374372,
AUTHOR = "Zhang, L. and Li, H.F. and Ma, L.",
TITLE = "An adaptive unsupervised clustering of pronunciation errors for
automatic pronunciation error detection",
BOOKTITLE = ICPR12,
YEAR = "2012",
PAGES = "1521-1525",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368476"}
@inproceedings{bb374373,
AUTHOR = "Rosales Perez, A. and Reyes Garcia, C.A. and Gonzalez, J.A. and Arch Tirado, E.",
TITLE = "Infant Cry Classification Using Genetic Selection of a Fuzzy Model",
BOOKTITLE = CIARP12,
YEAR = "2012",
PAGES = "212-219",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368477"}
@inproceedings{bb374374,
AUTHOR = "Gonzalez, D.C. and Ling, L.L. and Violaro, F.",
TITLE = "Analysis of the Multifractal Nature of Speech Signals",
BOOKTITLE = CIARP12,
YEAR = "2012",
PAGES = "740-748",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368478"}
@inproceedings{bb374375,
AUTHOR = "Tanveer, S. and Muhammad, A. and Martinez Enriquez, A.M. and Escalada Imaz, G.",
TITLE = "Phonetic Unification of Multiple Accents for Spanish and Arabic
Languages",
BOOKTITLE = MCPR12,
YEAR = "2012",
PAGES = "323-333",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368479"}
@inproceedings{bb374376,
AUTHOR = "Falek, L. and Teffahi, H. and Djeradi, A.",
TITLE = "Methodology for Acoustic Characterization of a Labial Constraint in
Speech Production",
BOOKTITLE = ICISP12,
YEAR = "2012",
PAGES = "131-141",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368480"}
@inproceedings{bb374377,
AUTHOR = "Krum, D.M. and Suma, E.A. and Bolas, M.",
TITLE = "Spatial misregistration of virtual human audio:
Implications of the precedence effect",
BOOKTITLE = "3DUI12",
YEAR = "2012",
PAGES = "147-148",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368481"}
@inproceedings{bb374378,
AUTHOR = "Yang, Y.J. and Zhang, H.H. and Guo, X.",
TITLE = "A pitch tracking method mixing ACF and AMDF algorithms based on
correlations",
BOOKTITLE = IASP11,
YEAR = "2011",
PAGES = "553-556",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368482"}
@inproceedings{bb374379,
AUTHOR = "Guo, S. and Gao, L. and Yu, H.Z.",
TITLE = "Research on Lhasa Tibetan prosodic model of journalese based on
respiratory signal",
BOOKTITLE = IASP11,
YEAR = "2011",
PAGES = "26-30",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368483"}
@inproceedings{bb374380,
AUTHOR = "Resmi, K. and Kumar, S. and Sardana, H.K. and Chhabra, R.",
TITLE = "Graphical Speech Training system for hearing impaired",
BOOKTITLE = ICIIP11,
YEAR = "2011",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368484"}
@inproceedings{bb374381,
AUTHOR = "Gomez, J.A. and Calvo, M.",
TITLE = "Improvements on Automatic Speech Segmentation at the Phonetic Level",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "557-564",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368485"}
@inproceedings{bb374382,
AUTHOR = "Le, P.N. and Epps, J. and Choi, E.H.C. and Ambikairajah, E.",
TITLE = "A Study of Voice Source and Vocal Tract Filter Based Features in
Cognitive Load Classification",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "4516-4519",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368486"}
@inproceedings{bb374383,
AUTHOR = "Stark, M. and Wohlmayr, M. and Pernkopf, F.",
TITLE = "Single Channel Speech Separation Using Source-Filter Representation",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "826-829",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368487"}
@inproceedings{bb374384,
AUTHOR = "Stadelmann, T. and Wang, Y.H. and Smith, M. and Ewerth, R. and Freisleben, B.",
TITLE = "Rethinking Algorithm Design and Development in Speech Processing",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "4476-4479",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368488"}
@inproceedings{bb374385,
AUTHOR = "Gonzalez Caravaca, G. and Toledano, D.T. and Puertas, M.",
TITLE = "Phone-Conditioned Suboptimal Wiener Filtering",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "4480-4483",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368489"}
@inproceedings{bb374386,
AUTHOR = "Sepehr, H. and Nooralahiyan, A.Y. and Brennan, P.V.",
TITLE = "Improving Performance of a Noise Reduction Algorithm by Switching the
Analysis Filter Bank",
BOOKTITLE = ICISP10,
YEAR = "2010",
PAGES = "262-271",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368490"}
@inproceedings{bb374387,
AUTHOR = "Kos, M. and Grasic, M. and Vlaj, D. and Kacic, Z.",
TITLE = "On-Line Speech/Music Segmentation for Broadcast News Domain",
BOOKTITLE = WSSIP09,
YEAR = "2009",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368491"}
@inproceedings{bb374388,
AUTHOR = "Grasic, M. and Kos, M. and Vlaj, D. and Kacic, Z.",
TITLE = "The Influence of Speech/Non-Speech Segmentation on On-Line and Off-Line
Speaker Segmentation Accuracy",
BOOKTITLE = WSSIP09,
YEAR = "2009",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368492"}
@inproceedings{bb374389,
AUTHOR = "Zuta, V.",
TITLE = "Voice Pleasantness of Female Voices and the Assessment of Physical
Characteristics",
BOOKTITLE = COST08,
YEAR = "2008",
PAGES = "116-125",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368493"}
@inproceedings{bb374390,
AUTHOR = "Stadelmann, T. and Heinzl, S. and Unterberger, M. and Freisleben, B.",
TITLE = "WebVoice: A Toolkit for Perceptual Insights into Speech Processing",
BOOKTITLE = CISP09,
YEAR = "2009",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368494"}
@inproceedings{bb374391,
AUTHOR = "Tang, Y.B. and Huang, R. and Wu, Z.Y.",
TITLE = "A 2.4kbps Multiband Characteristic Waveform Interpolation Speech Coding
Algorithm",
BOOKTITLE = CISP09,
YEAR = "2009",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368495"}
@inproceedings{bb374392,
AUTHOR = "Zou, X. and Zhang, X.W.",
TITLE = "A 450bps Speech Coding Algorithm Based on Multi-Mode Matrix
Quantization",
BOOKTITLE = CISP09,
YEAR = "2009",
PAGES = "1-3",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368496"}
@inproceedings{bb374393,
AUTHOR = "Li, X.K. and Deng, Y.",
TITLE = "Combining speech energy and edge information for fast and efficient
voice activity detection in noisy environments",
BOOKTITLE = ICPR08,
YEAR = "2008",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368497"}
@inproceedings{bb374394,
AUTHOR = "Kukharchik, P. and Kheidorov, I. and Bovbel, E. and Ladeev, D.",
TITLE = "Speech Signal Processing Based on Wavelets and SVM for Vocal Tract
Pathology Detection",
BOOKTITLE = ICISP08,
YEAR = "2008",
PAGES = "192-199",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368498"}
@inproceedings{bb374395,
AUTHOR = "Nagesha and Kumar, G.H.",
TITLE = "Signal Resampling Technique Combining Level Crossing and Auditory
Features",
BOOKTITLE = PReMI07,
YEAR = "2007",
PAGES = "447-454",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368499"}
@inproceedings{bb374396,
AUTHOR = "Varallyay, G.",
TITLE = "SSM: A Novel Method to Recognize the Fundamental Frequency in Voice
Signals",
BOOKTITLE = CIARP07,
YEAR = "2007",
PAGES = "88-95",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368500"}
@inproceedings{bb374397,
AUTHOR = "Ferrer, C.A. and Gonzalez, E. and Hernandez Diaz, M.E.",
TITLE = "Evaluation of Time and Frequency Domain-Based Methods for the
Estimation of Harmonics-to-Noise-Ratios in Voice Signals",
BOOKTITLE = CIARP06,
YEAR = "2006",
PAGES = "406-415",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368501"}
@inproceedings{bb374398,
AUTHOR = "Xue, W. and Du, S. and Fang, C.Z. and Ye, Y.X.",
TITLE = "Voice Activity Detection Using Wavelet-Based Multiresolution Spectrum
and Support Vector Machines and Audio Mixing Algorithm",
BOOKTITLE = CVHCI06,
YEAR = "2006",
PAGES = "78-88",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368502"}
@inproceedings{bb374399,
AUTHOR = "Garcia Perera, L.P. and Nolazco Flores, J.A. and Mex Perera, C.",
TITLE = "Cryptographic-Speech-Key Generation Architecture Improvements",
BOOKTITLE = IbPRIA05,
YEAR = "2005",
PAGES = "II:579",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1024sa1.html#TT368503"}
Last update:Jan 8, 2026 at 12:52:16