@article{bb374600,
        AUTHOR = "Wang, H. and Yang, Y.F. and Liu, S. and Li, J. and Meng, L. and Liu, Y.Q. and Zhou, J.M. and Sun, H.Q. and Lu, Y. and Qin, Y.",
        TITLE = "StreamMel: Real-Time Zero-Shot Text-to-Speech Via Interleaved
Continuous Autoregressive Modeling",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "3530-3534",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368704"}

@article{bb374601,
        AUTHOR = "Li, L. and Cong, G.X. and Qi, Y.K. and Zha, Z.J. and Wu, Q. and Sheng, Q.Z. and Huang, Q.M. and Yang, M.H.",
        TITLE = "Dubbing Movies via Hierarchical Phoneme Modeling and Acoustic
Diffusion Denoising",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "10361-10377",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368705"}

@article{bb374602,
        AUTHOR = "Gao, X.X. and Zhang, H. and Chen, N.F.",
        TITLE = "Prompt-Unseen-Emotion: Mixed Emotional Speech Synthesis With
Prompt-LLM Contextual Knowledge",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "4259-4263",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368706"}

@article{bb374603,
        AUTHOR = "Lee, K. and Hong, S. and Chun, S.Y.",
        TITLE = "Robust watermarks for audio diffusion models by quadrature amplitude
modulation",
        JOURNAL = PRL,
        VOLUME = "198",
        YEAR = "2025",
        PAGES = "22-28",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368707"}

@article{bb374604,
        AUTHOR = "Inoue, S. and Zhou, K. and Wang, S. and Li, H.Z.",
        TITLE = "Hierarchical Control of Emotion Rendering in Speech Synthesis",
        JOURNAL = AffCom,
        VOLUME = "16",
        YEAR = "2025",
        NUMBER = "4",
        MONTH = "October",
        PAGES = "3316-3328",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368708"}

@article{bb374605,
        AUTHOR = "Cha, H. and Um, S. and Kim, M. and Kim, C. and Lee, S. and Kang, H.G.",
        TITLE = "Content-Aware Style Augmentation for Zero-Shot Voice Conversion With
Short Target Speech",
        JOURNAL = SPLetters,
        VOLUME = "33",
        YEAR = "2026",
        PAGES = "66-70",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368709"}

@inproceedings{bb374606,
        AUTHOR = "Liu, J. and Geddes, J. and Guo, Z.Y. and Jiang, H. and Nandwana, M.K.",
        TITLE = "Smooth Cache: A Universal Inference Acceleration Technique for
Diffusion Transformers",
        BOOKTITLE = LargeVM25,
        YEAR = "2025",
        PAGES = "3220-3229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368710"}

@inproceedings{bb374607,
        AUTHOR = "Kushwaha, S.S. and Tian, Y.P.",
        TITLE = "VinTAGe: Joint Video and Text Conditioning for Holistic Audio
Generation",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "13529-13539",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368711"}

@inproceedings{bb374608,
        AUTHOR = "Kim, J.H. and Choi, J. and Kim, J.H. and Jung, C. and Chung, J.S.",
        TITLE = "From Faces to Voices: Learning Hierarchical Representations for
High-quality Video-to-Speech",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "15874-15884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368712"}

@inproceedings{bb374609,
        AUTHOR = "Cong, G.X. and Pan, J. and Li, L. and Qi, Y.K. and Peng, Y.X. and van den Hengel, A.J. and Yang, J. and Huang, Q.M.",
        TITLE = "EmoDubber: Towards High Quality and Emotion Controllable Movie
Dubbing",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "15863-15873",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368713"}

@inproceedings{bb374610,
        AUTHOR = "Zhang, Z.D. and Li, L. and Yan, C.G. and Liu, C.S. and van den Hengel, A.J. and Qi, Y.K.",
        TITLE = "Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled
Prosody Adapting for Movie Dubbing",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "172-182",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368714"}

@inproceedings{bb374611,
        AUTHOR = "Rai, A. and Sridhar, S.",
        TITLE = "EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "4935-4946",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368715"}

@inproceedings{bb374612,
        AUTHOR = "Yadav, A.K.S. and Bhagtani, K. and Salvi, D. and Bestagini, P. and Delp, E.J.",
        TITLE = "FairSSD: Understanding Bias in Synthetic Speech Detectors",
        BOOKTITLE = WMF24,
        YEAR = "2024",
        PAGES = "4418-4428",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368716"}

@inproceedings{bb374613,
        AUTHOR = "Cuccovillo, L. and Gerhardt, M. and Aichroth, P.",
        TITLE = "Audio Transformer for Synthetic Speech Detection via Multi-Formant
Analysis",
        BOOKTITLE = WMF24,
        YEAR = "2024",
        PAGES = "4409-4417",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368717"}

@inproceedings{bb374614,
        AUTHOR = "Cong, G.X. and Li, L. and Qi, Y.K. and Zha, Z.J. and Wu, Q. and Wang, W.Y. and Jiang, B. and Yang, M.H. and Huang, Q.M.",
        TITLE = "Learning to Dub Movies via Hierarchical Prosody Models",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "14687-14697",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368718"}

@inproceedings{bb374615,
        AUTHOR = "Hsu, W.N. and Remez, T. and Shi, B. and Donley, J. and Adi, Y.",
        TITLE = "ReVISE: Self-Supervised Speech Resynthesis with Visual Input for
Universal and Generalized Speech Regeneration",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "18796-18806",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368719"}

@inproceedings{bb374616,
        AUTHOR = "Sun, C.Z. and Jia, S. and Hou, S.W. and Lyu, S.W.",
        TITLE = "AI-Synthesized Voice Detection Using Neural Vocoder Artifacts",
        BOOKTITLE = WMF23,
        YEAR = "2023",
        PAGES = "904-912",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368720"}

@inproceedings{bb374617,
        AUTHOR = "Noufi, C. and May, L. and Berger, J.",
        TITLE = "The Role of Vocal Persona in Natural and Synthesized Speech",
        BOOKTITLE = FG23,
        YEAR = "2023",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368721"}

@inproceedings{bb374618,
        AUTHOR = "Hwang, I.S. and Lee, S.H. and Lee, S.W.",
        TITLE = "StyleVC: Non-Parallel Voice Conversion with Adversarial Style
Generalization",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "23-30",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368722"}

@inproceedings{bb374619,
        AUTHOR = "Wang, W.B. and Song, Y. and Jha, S.",
        TITLE = "Autolv: Automatic Lecture Video Generator",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "1086-1090",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368723"}

@inproceedings{bb374620,
        AUTHOR = "Borzi, S. and Giudice, O. and Stanco, F. and Allegra, D.",
        TITLE = "Is synthetic voice detection research going into the right direction?",
        BOOKTITLE = WMF22,
        YEAR = "2022",
        PAGES = "71-80",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368724"}

@inproceedings{bb374621,
        AUTHOR = "Hassid, M. and Ramanovich, M.T. and Shillingford, B. and Wang, M. and Jia, Y. and Remez, T.",
        TITLE = "More than Words: In-the-Wild Visually-Driven Prosody for
Text-to-Speech",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "10577-10587",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368725"}

@inproceedings{bb374622,
        AUTHOR = "Kwak, I.Y. and Kwag, S. and Lee, J. and Huh, J.H. and Lee, C.H. and Jeon, Y.B. and Hwang, J.H. and Yoon, J.W.",
        TITLE = "ResMax: Detecting Voice Spoofing Attacks with Residual Network and
Max Feature Map",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "4837-4844",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368726"}

@inproceedings{bb374623,
        AUTHOR = "Wang, D.H. and Wang, R. and Dong, L. and Yan, D. and Ren, Y.M.",
        TITLE = "Efficient Generation of Speech Adversarial Examples with Generative
Model",
        BOOKTITLE = IWDW20,
        YEAR = "2020",
        PAGES = "251-264",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368727"}

@inproceedings{bb374624,
        AUTHOR = "Zhou, H. and Liu, Z. and Xu, X. and Luo, P. and Wang, X.",
        TITLE = "Vision-Infused Deep Audio Inpainting",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "283-292",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368728"}

@inproceedings{bb374625,
        AUTHOR = "Bailer, W. and Wijnants, M. and Lievens, H. and Claes, S.",
        TITLE = "Multimedia Analytics Challenges and Opportunities for Creating
Interactive Radio Content",
        BOOKTITLE = MMMod20,
        YEAR = "2020",
        PAGES = "II:375-387",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368729"}

@inproceedings{bb374626,
        AUTHOR = "Huang, T. and Wang, H.X. and Chen, Y. and He, P.S.",
        TITLE = "GRU-SVM Model for Synthetic Speech Detection",
        BOOKTITLE = IWDW19,
        YEAR = "2019",
        PAGES = "115-125",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368730"}

@inproceedings{bb374627,
        AUTHOR = "Wong, A. and Xu, A. and Dudek, G.",
        TITLE = "Investigating Trust Factors in Human-Robot Shared Control:
Implicit Gender Bias Around Robot Voice",
        BOOKTITLE = CRV19,
        YEAR = "2019",
        PAGES = "195-200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368731"}

@inproceedings{bb374628,
        AUTHOR = "Xiao, L. and Wang, Z.",
        TITLE = "Dense Convolutional Recurrent Neural Network for Generalized Speech
Animation",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "633-638",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368732"}

@inproceedings{bb374629,
        AUTHOR = "Shah, N.J. and Patil, H.A.",
        TITLE = "Analysis of Features and Metrics for Alignment in Text-Dependent Voice
Conversion",
        BOOKTITLE = PReMI17,
        YEAR = "2017",
        PAGES = "299-307",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368733"}

@inproceedings{bb374630,
        AUTHOR = "Rybarova, R. and Drozd, I. and Rozinaj, G.",
        TITLE = "GUI for interactive speech synthesis",
        BOOKTITLE = WSSIP16,
        YEAR = "2016",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368734"}

@inproceedings{bb374631,
        AUTHOR = "Coto Jimenez, M. and Goddard Close, J.",
        TITLE = "LSTM Deep Neural Networks Postfiltering for Improving the Quality of
Synthetic Voices",
        BOOKTITLE = MCPR16,
        YEAR = "2016",
        PAGES = "280-289",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368735"}

@inproceedings{bb374632,
        AUTHOR = "Vasek, M. and Rozinaj, G. and Rybarova, R.",
        TITLE = "Letter-To-Sound conversion for speech synthesizer",
        BOOKTITLE = WSSIP16,
        YEAR = "2016",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368736"}

@inproceedings{bb374633,
        AUTHOR = "Rybarova, R. and del Corral, G. and Rozinaj, G.",
        TITLE = "Diphone spanish text-to-speech synthesizer",
        BOOKTITLE = WSSIP15,
        YEAR = "2015",
        PAGES = "121-124",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368737"}

@inproceedings{bb374634,
        AUTHOR = "Verma, R. and Sarkar, P. and Rao, K.S.",
        TITLE = "Conversion of neutral speech to storytelling style speech",
        BOOKTITLE = ICAPR15,
        YEAR = "2015",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368738"}

@inproceedings{bb374635,
        AUTHOR = "Narendra, N.P. and Rao, K.S.",
        TITLE = "Optimal residual frame based source modeling for HMM-based speech
synthesis",
        BOOKTITLE = ICAPR15,
        YEAR = "2015",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368739"}

@inproceedings{bb374636,
        AUTHOR = "Wang, Y. and Tao, J.H. and Yang, M.H. and Li, Y.",
        TITLE = "Extended Decision Tree with or Relationship for HMM-Based Speech
Synthesis",
        BOOKTITLE = ACPR13,
        YEAR = "2013",
        PAGES = "225-229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368740"}

@inproceedings{bb374637,
        AUTHOR = "Gao, L. and Yu, H.Z. and Zhang, J.H. and Fang, H.P.",
        TITLE = "Research on HMM_based speech synthesis for Lhasa dialect",
        BOOKTITLE = IASP11,
        YEAR = "2011",
        PAGES = "429-433",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368741"}

@inproceedings{bb374638,
        AUTHOR = "Chakraborty, R. and Garain, U.",
        TITLE = "Role of Synthetically Generated Samples on Speech Recognition in a
Resource-Scarce Language",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "1618-1621",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368742"}

@inproceedings{bb374639,
        AUTHOR = "Rao, K.S. and Maity, S. and Taru, A. and Koolagudi, S.G.",
        TITLE = "Unit Selection Using Linguistic, Prosodic and Spectral Distance for
Developing Text-to-Speech System in Hindi",
        BOOKTITLE = PReMI09,
        YEAR = "2009",
        PAGES = "531-536",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368743"}

@inproceedings{bb374640,
        AUTHOR = "Bahrampour, A. and Barkhoda, W. and Azami, B.Z.",
        TITLE = "Implementation of Three Text to Speech Systems for Kurdish Language",
        BOOKTITLE = CIARP09,
        YEAR = "2009",
        PAGES = "321-328",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368744"}

@inproceedings{bb374641,
        AUTHOR = "Shirbahadurkar, S.D. and Bormane, D.S.",
        TITLE = "Marathi Language Speech Synthesizer Using Concatenative Synthesis
Strategy (Spoken in Maharashtra, India)",
        BOOKTITLE = ICMV09,
        YEAR = "2009",
        PAGES = "181-185",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368745"}

@inproceedings{bb374642,
        AUTHOR = "Tuckova, J. and Holub, J. and Dubeda, T.",
        TITLE = "Technical and Phonetic Aspects of Speech Quality Assessment:
The Case of Prosody Synthesis",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "126-132",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368746"}

@inproceedings{bb374643,
        AUTHOR = "Bauer, D. and Kannampuzha, J. and Kroger, B.J.",
        TITLE = "Articulatory Speech Re-synthesis:
Profiting from Natural Acoustic Speech Data",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "344-355",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368747"}

@inproceedings{bb374644,
        AUTHOR = "Gu, H.Y. and Cai, C.L. and Cai, S.F.",
        TITLE = "An HNM-Based Speaker-Nonspecific Timbre Transformation Scheme for
Speech Synthesis",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT368748"}

@article{bb374645,
        AUTHOR = "Lung, S.Y. and Chen, C.C.T.",
        TITLE = "A new approach for text-independent speaker recognition",
        JOURNAL = PR,
        VOLUME = "33",
        YEAR = "2000",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1401-1403",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368749"}

@article{bb374646,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Multi-resolution form of SVD for text-independent speaker recognition",
        JOURNAL = PR,
        VOLUME = "35",
        YEAR = "2002",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1637-1639",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368750"}

@article{bb374647,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Further reduced form of wavelet feature for text independent speaker
recognition",
        JOURNAL = PR,
        VOLUME = "37",
        YEAR = "2004",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1565-1566",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368751"}

@article{bb374648,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Feature extracted from wavelet eigenfunction estimation for
text-independent speaker recognition",
        JOURNAL = PR,
        VOLUME = "37",
        YEAR = "2004",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1543-1544",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368752"}

@article{bb374649,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Wavelet feature domain adaptive noise reduction using learning
algorithm for text-independent speaker recognition",
        JOURNAL = PR,
        VOLUME = "40",
        YEAR = "2007",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2603-2606",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368753"}

@article{bb374650,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Efficient text independent speaker recognition with wavelet feature
selection based multilayered neural network using supervised learning
algorithm",
        JOURNAL = PR,
        VOLUME = "40",
        YEAR = "2007",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "3616-3620",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368754"}

@article{bb374651,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Distributed genetic algorithm for Gaussian mixture model based speaker
identification",
        JOURNAL = PR,
        VOLUME = "36",
        YEAR = "2003",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2479-2481",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368755"}

@article{bb374652,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Adaptive fuzzy wavelet algorithm for text-independent speaker
recognition",
        JOURNAL = PR,
        VOLUME = "37",
        YEAR = "2004",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2095-2096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368756"}

@article{bb374653,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Wavelet feature selection based neural networks with application to the
text independent speaker identification",
        JOURNAL = PR,
        VOLUME = "39",
        YEAR = "2006",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1518-1521",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368757"}

@article{bb374654,
        AUTHOR = "Lung, S.Y.",
        TITLE = "Feature extracted from wavelet decomposition using biorthogonal Riesz
basis for text-independent speaker recognition",
        JOURNAL = PR,
        VOLUME = "41",
        YEAR = "2008",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "3068-3070",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368758"}

@article{bb374655,
        AUTHOR = "Chen, K. and Wu, T.Y. and Zhang, H.J.",
        TITLE = "On the use of nearest feature line for speaker identification",
        JOURNAL = PRL,
        VOLUME = "23",
        YEAR = "2002",
        NUMBER = "14",
        MONTH = "December",
        PAGES = "1735-1746",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368759"}

@article{bb374656,
        AUTHOR = "Ramachandran, R.P. and Farrell, K.R. and Ramachandran, R. and Mammone, R.J.",
        TITLE = "Speaker recognition:
general classifier approaches and data fusion methods",
        JOURNAL = PR,
        VOLUME = "35",
        YEAR = "2002",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "2801-2821",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368760"}

@article{bb374657,
        AUTHOR = "Chen, K.",
        TITLE = "Towards better making a decision in speaker verification",
        JOURNAL = PR,
        VOLUME = "36",
        YEAR = "2003",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "329-346",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368761"}

@article{bb374658,
        AUTHOR = "Rodriguez Linares, L. and Garcia Mateo, C. and Alba Castro, J.L.",
        TITLE = "On combining classifiers for speaker authentication",
        JOURNAL = PR,
        VOLUME = "36",
        YEAR = "2003",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "347-359",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368762"}

@article{bb374659,
        AUTHOR = "Damper, R.I. and Higgins, J.E.",
        TITLE = "Improving speaker identification in noise by subband processing and
decision fusion",
        JOURNAL = PRL,
        VOLUME = "24",
        YEAR = "2003",
        NUMBER = "13",
        MONTH = "September",
        PAGES = "2167-2173",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368763"}

@article{bb374660,
        AUTHOR = "Besacier, L. and Mayorga, P. and Bonastre, J.F. and Fredouille, C. and Meignier, S.",
        TITLE = "Overview of compression and packet loss effects in speech biometrics",
        JOURNAL = VISP,
        VOLUME = "150",
        YEAR = "2003",
        NUMBER = "6",
        MONTH = "December",
        PAGES = "372-376",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368764"}

@inproceedings{bb374661,
        AUTHOR = "Besacier, L. and Bonastre, J.F.",
        TITLE = "Time and frequency pruning for speaker identification",
        BOOKTITLE = ICPR98,
        YEAR = "1998",
        PAGES = "Vol II: 1619-1621",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368765"}

@article{bb374662,
        AUTHOR = "Rodriguez Linares, L. and Garcia Mateo, C.",
        TITLE = "Application of fusion techniques to speaker authentication over ip
networks",
        JOURNAL = VISP,
        VOLUME = "150",
        YEAR = "2003",
        NUMBER = "6",
        MONTH = "December",
        PAGES = "377-382",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368766"}

@article{bb374663,
        AUTHOR = "Chen, C.C.T. and Chen, C.T. and Hou, C.K.",
        TITLE = "Speaker identification using hybrid Karhunen-Loeve transform and
Gaussian mixture model approach",
        JOURNAL = PR,
        VOLUME = "37",
        YEAR = "2004",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1073-1075",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368767"}

@article{bb374664,
        AUTHOR = "Lee, K.Y.",
        TITLE = "Local fuzzy PCA based GMM with dimension reduction on speaker
identification",
        JOURNAL = PRL,
        VOLUME = "25",
        YEAR = "2004",
        NUMBER = "16",
        MONTH = "December",
        PAGES = "1811-1817",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368768"}

@article{bb374665,
        AUTHOR = "Mashao, D.J. and Skosan, M.",
        TITLE = "Combining classifier decisions for robust speaker identification",
        JOURNAL = PR,
        VOLUME = "39",
        YEAR = "2006",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "147-155",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368769"}

@article{bb374666,
        AUTHOR = "Skosan, M. and Mashao, D.J.",
        TITLE = "Modified Segmental Histogram Equalization for robust speaker
verification",
        JOURNAL = PRL,
        VOLUME = "27",
        YEAR = "2006",
        NUMBER = "5",
        MONTH = "April",
        PAGES = "479-486",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368770"}

@article{bb374667,
        AUTHOR = "Ariyaeeinia, A.M. and Fortuna, J. and Sivakumaran, P. and Malegaonkar, A.",
        TITLE = "Verification effectiveness in open-set speaker identification",
        JOURNAL = VISP,
        VOLUME = "153",
        YEAR = "2006",
        NUMBER = "5",
        MONTH = "October",
        PAGES = "618-624",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368771"}

@article{bb374668,
        AUTHOR = "Zhou, G. and Mikhael, W.B.",
        TITLE = "Speaker identification based on adaptive discriminative vector
quantisation",
        JOURNAL = VISP,
        VOLUME = "153",
        YEAR = "2006",
        NUMBER = "6",
        MONTH = "December",
        PAGES = "754-760",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368772"}

@article{bb374669,
        AUTHOR = "Park, C.M. and Thapa, D. and Wang, G.N.",
        TITLE = "Speech authentication system using digital watermarking and pattern
recovery",
        JOURNAL = PRL,
        VOLUME = "28",
        YEAR = "2007",
        NUMBER = "8",
        MONTH = "June",
        PAGES = "931-938",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368773"}

@article{bb374670,
        AUTHOR = "Faundez Zanuy, M. and Hagmuller, M. and Kubin, G.",
        TITLE = "Speaker identification security improvement by means of speech
watermarking",
        JOURNAL = PR,
        VOLUME = "40",
        YEAR = "2007",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "3027-3034",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368774"}

@article{bb374671,
        AUTHOR = "Chetouani, M. and Faundez Zanuy, M. and Gas, B. and Zarader, J.L.",
        TITLE = "Investigation on LP-residual representations for speaker identification",
        JOURNAL = PR,
        VOLUME = "42",
        YEAR = "2009",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "487-494",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368775"}

@article{bb374672,
        AUTHOR = "Kinnunen, T. and Saastamoinen, J. and Hautamaki, V. and Vinni, M. and Franti, P.",
        TITLE = "Comparative evaluation of maximum a Posteriori vector quantization and
Gaussian mixture models in speaker verification",
        JOURNAL = PRL,
        VOLUME = "30",
        YEAR = "2009",
        NUMBER = "4",
        MONTH = "March",
        PAGES = "341-347",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368776"}

@article{bb374673,
        AUTHOR = "Chao, Y.H. and Tsai, W.H. and Wang, H.M. and Chang, R.C.",
        TITLE = "Improving the characterization of the alternative hypothesis via
minimum verification error training with applications to speaker
verification",
        JOURNAL = PR,
        VOLUME = "42",
        YEAR = "2009",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1351-1360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368777"}

@article{bb374674,
        AUTHOR = "Temko, A. and Nadeu, C.",
        TITLE = "Acoustic event detection in meeting-room environments",
        JOURNAL = PRL,
        VOLUME = "30",
        YEAR = "2009",
        NUMBER = "14",
        MONTH = "October",
        PAGES = "1281-1288",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368778"}

@article{bb374675,
        AUTHOR = "Kim, S. and Ji, M.Y. and Kim, H.",
        TITLE = "Robust speaker recognition based on filtering in autocorrelation domain
and sub-band feature recombination",
        JOURNAL = PRL,
        VOLUME = "31",
        YEAR = "2010",
        NUMBER = "7",
        MONTH = "May",
        PAGES = "593-599",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368779"}

@article{bb374676,
        AUTHOR = "Li, H. and Ma, B. and Lee, K.A.",
        TITLE = "Spoken Language Recognition: From Fundamentals to Practice",
        JOURNAL = PIEEE,
        VOLUME = "100",
        YEAR = "2013",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1136-1159",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368780"}

@article{bb374677,
        AUTHOR = "Li, H. and Ma, B.",
        TITLE = "TechWare: Speaker and Spoken Language Recognition Resources",
        JOURNAL = SPMag,
        VOLUME = "27",
        YEAR = "2010",
        NUMBER = "6",
        PAGES = "139-142",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368781"}

@article{bb374678,
        AUTHOR = "Ajmera, P.K. and Jadhav, D.V. and Holambe, R.S.",
        TITLE = "Text-independent speaker identification using Radon and discrete cosine
transforms based features from speech spectrogram",
        JOURNAL = PR,
        VOLUME = "44",
        YEAR = "2011",
        NUMBER = "10-11",
        MONTH = "October",
        PAGES = "2749-2759",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368782"}

@article{bb374679,
        AUTHOR = "Kinnunen, T. and Sidoroff, I. and Tuononen, M. and Franti, P.",
        TITLE = "Comparison of clustering methods:
A case study of text-independent speaker modeling",
        JOURNAL = PRL,
        VOLUME = "32",
        YEAR = "2011",
        NUMBER = "13",
        MONTH = "October",
        PAGES = "1604-1617",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368783"}

@inproceedings{bb374680,
        AUTHOR = "Kinnunen, T. and Karpov, E. and Franti, P.",
        TITLE = "A Speaker Pruning Algorithm for Real-Time Speaker Identification",
        BOOKTITLE = AVBPA03,
        YEAR = "2003",
        PAGES = "639-646",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368784"}

@inproceedings{bb374681,
        AUTHOR = "Kinnunen, T. and Franti, P.",
        TITLE = "Speaker Discriminative Weighting Method for VQ-Based Speaker
Identification",
        BOOKTITLE = AVBPA01,
        YEAR = "2001",
        PAGES = "150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368785"}

@article{bb374682,
        AUTHOR = "Zao, L. and Coelho, R.",
        TITLE = "Colored Noise Based Multicondition Training Technique for Robust
Speaker Identification",
        JOURNAL = SPLetters,
        VOLUME = "18",
        YEAR = "2011",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "675-678",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368786"}

@article{bb374683,
        AUTHOR = "Hanilci, C. and Kinnunen, T. and Ertas, F. and Saeidi, R. and Pohjalainen, J. and Alku, P.",
        TITLE = "Regularized All-Pole Models for Speaker Verification Under Noisy
Environments",
        JOURNAL = SPLetters,
        VOLUME = "19",
        YEAR = "2012",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "163-166",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368787"}

@article{bb374684,
        AUTHOR = "Salamin, H. and Vinciarelli, A.",
        TITLE = "Automatic Role Recognition in Multiparty Conversations: An Approach
Based on Turn Organization, Prosody, and Conditional Random Fields",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "2",
        PAGES = "338-345",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368788"}

@article{bb374685,
        AUTHOR = "Tang, H. and Chu, S. and Hasegawa Johnson, M. and Huang, T.S.",
        TITLE = "Partially Supervised Speaker Clustering",
        JOURNAL = PAMI,
        VOLUME = "34",
        YEAR = "2012",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "959-971",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368789"}

@article{bb374686,
        AUTHOR = "Montalvao, J. and Araujo, M.R.R.",
        TITLE = "Is masking a relevant aspect lacking in MFCC? A speaker verification
perspective",
        JOURNAL = PRL,
        VOLUME = "33",
        YEAR = "2012",
        NUMBER = "16",
        MONTH = "December",
        PAGES = "2156-2165",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368790"}

@article{bb374687,
        AUTHOR = "Garimella, S. and Mallidi, S.H. and Hermansky, H.",
        TITLE = "Regularized Auto-Associative Neural Networks for Speaker Verification",
        JOURNAL = SPLetters,
        VOLUME = "19",
        YEAR = "2012",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "841-844",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368791"}

@article{bb374688,
        AUTHOR = "Sahidullah, M. and Saha, G.",
        TITLE = "A Novel Windowing Technique for Efficient Computation of MFCC for
Speaker Recognition",
        JOURNAL = SPLetters,
        VOLUME = "20",
        YEAR = "2013",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "149-152",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368792"}

@article{bb374689,
        AUTHOR = "Vallet, F. and Essid, S. and Carrive, J.",
        TITLE = "A Multimodal Approach to Speaker Diarization on TV Talk-Shows",
        JOURNAL = MultMed,
        VOLUME = "15",
        YEAR = "2013",
        NUMBER = "3",
        PAGES = "509-520",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368793"}

@article{bb374690,
        AUTHOR = "Inthavisas, K. and Lopresti, D.",
        TITLE = "Secure speech biometric templates for user authentication",
        JOURNAL = IET-Bio,
        VOLUME = "1",
        YEAR = "2012",
        NUMBER = "1",
        MONTH = "March",
        PAGES = "46-54",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368794"}

@article{bb374691,
        AUTHOR = "Pillay, S. and Ariyaeeinia, A. and Sivakumaran, P. and Pawlewski, M.",
        TITLE = "Effective speaker verification via dynamic mismatch compensation",
        JOURNAL = IET-Bio,
        VOLUME = "1",
        YEAR = "2012",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "130-135",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368795"}

@article{bb374692,
        AUTHOR = "Bhardwaj, S. and Srivastava, S. and Hanmandlu, M. and Gupta, J.R.P.",
        TITLE = "GFM-Based Methods for Speaker Identification",
        JOURNAL = Cyber,
        VOLUME = "43",
        YEAR = "2013",
        NUMBER = "3",
        PAGES = "1047-1058",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368796"}

@article{bb374693,
        AUTHOR = "Pekhovsky, T. and Sizov, A.",
        TITLE = "Comparison between supervised and unsupervised learning of
probabilistic linear discriminant analysis mixture models for speaker
verification",
        JOURNAL = PRL,
        VOLUME = "34",
        YEAR = "2013",
        NUMBER = "11",
        MONTH = "August",
        PAGES = "1307-1313",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368797"}

@article{bb374694,
        AUTHOR = "Yaman, S. and Pelecanos, J.",
        TITLE = "Using Polynomial Kernel Support Vector Machines for Speaker
Verification",
        JOURNAL = SPLetters,
        VOLUME = "20",
        YEAR = "2013",
        NUMBER = "9",
        PAGES = "901-904",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368798"}

@article{bb374695,
        AUTHOR = "Bin Amin, T. and Marziliano, P. and German, J.S.",
        TITLE = "Glottal and Vocal Tract Characteristics of Voice Impersonators",
        JOURNAL = MultMed,
        VOLUME = "16",
        YEAR = "2014",
        NUMBER = "3",
        MONTH = "April",
        PAGES = "668-678",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368799"}

@article{bb374696,
        AUTHOR = "Sarkar, A.K. and Do, C.T. and Le, V.B. and Barras, C.",
        TITLE = "Combination of Cepstral and Phonetically Discriminative Features for
Speaker Verification",
        JOURNAL = SPLetters,
        VOLUME = "21",
        YEAR = "2014",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1040-1044",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368800"}

@article{bb374697,
        AUTHOR = "Yang, H. and Xu, Y. and Huang, H. and Zhou, R. and Yan, Y.",
        TITLE = "Voice biometrics using linear Gaussian model",
        JOURNAL = IET-Bio,
        VOLUME = "3",
        YEAR = "2014",
        NUMBER = "1",
        MONTH = "March",
        PAGES = "9-15",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368801"}

@article{bb374698,
        AUTHOR = "Ribas Gonzalez, D. and Calvo de Lara, J.R.",
        TITLE = "Feature classification criterion for missing features mask estimation
in robust speaker recognition",
        JOURNAL = SIViP,
        VOLUME = "8",
        YEAR = "2014",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "365-375",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368802"}

@article{bb374699,
        AUTHOR = "Hernandez Sierra, G. and Calvo, J.R. and Bonastre, J.F. and Bousquet, P.M.",
        TITLE = "Session compensation using binary speech representation for speaker
recognition",
        JOURNAL = PRL,
        VOLUME = "49",
        YEAR = "2014",
        NUMBER = "1",
        PAGES = "17-23",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024.html#TT368803"}

Last update:Jan 8, 2026 at 12:52:16