@article{bb384800,
        AUTHOR = "Lee, J. and Shin, Y. and Chang, J.H.",
        TITLE = "Differentiable Duration Refinement Using Internal Division for
Non-Autoregressive Text-to-Speech",
        JOURNAL = SPLetters,
        VOLUME = "31",
        YEAR = "2024",
        PAGES = "3154-3158",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378881"}

@article{bb384801,
        AUTHOR = "Xu, X. and Ma, Z.Y. and Wu, M.Y. and Yu, K.",
        TITLE = "Towards Weakly Supervised Text-to-Audio Grounding",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "11126-11138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378882"}

@article{bb384802,
        AUTHOR = "Kim, M. and Jeong, M. and Lee, J.Y. and Kim, N.S.",
        TITLE = "SegINR: Segment-Wise Implicit Neural Representation for Sequence
Alignment in Neural Text-to-Speech",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "646-650",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378883"}

@article{bb384803,
        AUTHOR = "Zheng, J.J. and Zhou, J. and Zheng, W.M. and Tao, L. and Kwan, H.K.",
        TITLE = "Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion
Representation of High Generalization Capability",
        JOURNAL = AffCom,
        VOLUME = "16",
        YEAR = "2025",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "68-82",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378884"}

@article{bb384804,
        AUTHOR = "Chen, K. and Huang, Z.H. and He, L. and Yan, Y.H.",
        TITLE = "UnitDiff: A Unit-Diffusion Model for Code-Switching Speech Synthesis",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "1051-1055",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378885"}

@article{bb384805,
        AUTHOR = "Chang, Y. and Ko, Y.J.",
        TITLE = "Soft engagement with pseudo initiatives for multi-party dialogue
generation",
        JOURNAL = PRL,
        VOLUME = "191",
        YEAR = "2025",
        PAGES = "103-109",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378886"}

@article{bb384806,
        AUTHOR = "He, Y.L. and Wang, H.X. and Qiu, Y.Q. and Cao, H.",
        TITLE = "ASSMark: Dual Defense Against Speech Synthesis Attack via Adversarial
Robust Watermarking",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "1870-1874",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378887"}

@article{bb384807,
        AUTHOR = "Wang, R. and Chen, L.P. and Lee, K.A. and Ling, Z.H.",
        TITLE = "Asynchronous Voice Anonymization by Learning From Speaker-Adversarial
Speech",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "1905-1909",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378888"}

@article{bb384808,
        AUTHOR = "Feng, Y. and Zhang, X.B. and Feng, F.Y. and Zhang, G.L. and Xu, L.T.",
        TITLE = "Robust and Imperceptible Watermarking Framework for Generative Audio
Models",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "3196-3200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378889"}

@article{bb384809,
        AUTHOR = "Lee, J. and Song, N.S. and Chang, J.H.",
        TITLE = "Vector Field Decomposition-Based Flow Matching for Zero-Shot
Cross-Lingual Text-to-Speech",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "3560-3564",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378890"}

@article{bb384810,
        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#TT378891"}

@article{bb384811,
        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#TT378892"}

@article{bb384812,
        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#TT378893"}

@article{bb384813,
        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#TT378894"}

@article{bb384814,
        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#TT378895"}

@article{bb384815,
        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#TT378896"}

@article{bb384816,
        AUTHOR = "Haji Ali, M. and Menapace, W. and Siarohin, A. and Balakrishnan, G. and Ordonez, V.",
        TITLE = "Taming Data and Transformers for Audio Generation",
        JOURNAL = IJCV,
        VOLUME = "134",
        YEAR = "2026",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "87",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1024ss1.html#TT378897"}

@inproceedings{bb384817,
        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#TT378898"}

@inproceedings{bb384818,
        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#TT378899"}

@inproceedings{bb384819,
        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#TT378900"}

@inproceedings{bb384820,
        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#TT378901"}

@inproceedings{bb384821,
        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#TT378902"}

@inproceedings{bb384822,
        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#TT378903"}

@inproceedings{bb384823,
        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#TT378904"}

@inproceedings{bb384824,
        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#TT378905"}

@inproceedings{bb384825,
        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#TT378906"}

@inproceedings{bb384826,
        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#TT378907"}

@inproceedings{bb384827,
        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#TT378908"}

@inproceedings{bb384828,
        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#TT378909"}

@inproceedings{bb384829,
        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#TT378910"}

@inproceedings{bb384830,
        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#TT378911"}

@inproceedings{bb384831,
        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#TT378912"}

@inproceedings{bb384832,
        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#TT378913"}

@inproceedings{bb384833,
        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#TT378914"}

@inproceedings{bb384834,
        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#TT378915"}

@inproceedings{bb384835,
        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#TT378916"}

@inproceedings{bb384836,
        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#TT378917"}

@inproceedings{bb384837,
        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#TT378918"}

@inproceedings{bb384838,
        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#TT378919"}

@inproceedings{bb384839,
        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#TT378920"}

@inproceedings{bb384840,
        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#TT378921"}

@inproceedings{bb384841,
        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#TT378922"}

@inproceedings{bb384842,
        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#TT378923"}

@inproceedings{bb384843,
        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#TT378924"}

@inproceedings{bb384844,
        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#TT378925"}

@inproceedings{bb384845,
        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#TT378926"}

@inproceedings{bb384846,
        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#TT378927"}

@inproceedings{bb384847,
        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#TT378928"}

@inproceedings{bb384848,
        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#TT378929"}

@inproceedings{bb384849,
        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#TT378930"}

@inproceedings{bb384850,
        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#TT378931"}

@inproceedings{bb384851,
        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#TT378932"}

@inproceedings{bb384852,
        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#TT378933"}

@inproceedings{bb384853,
        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#TT378934"}

@inproceedings{bb384854,
        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#TT378935"}

@inproceedings{bb384855,
        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#TT378936"}

@article{bb384856,
        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#TT378937"}

@article{bb384857,
        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#TT378938"}

@article{bb384858,
        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#TT378939"}

@article{bb384859,
        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#TT378940"}

@article{bb384860,
        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#TT378941"}

@article{bb384861,
        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#TT378942"}

@article{bb384862,
        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#TT378943"}

@article{bb384863,
        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#TT378944"}

@article{bb384864,
        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#TT378945"}

@article{bb384865,
        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#TT378946"}

@article{bb384866,
        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#TT378947"}

@article{bb384867,
        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#TT378948"}

@article{bb384868,
        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#TT378949"}

@article{bb384869,
        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#TT378950"}

@article{bb384870,
        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#TT378951"}

@article{bb384871,
        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#TT378952"}

@inproceedings{bb384872,
        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#TT378953"}

@article{bb384873,
        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#TT378954"}

@article{bb384874,
        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#TT378955"}

@article{bb384875,
        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#TT378956"}

@article{bb384876,
        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#TT378957"}

@article{bb384877,
        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#TT378958"}

@article{bb384878,
        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#TT378959"}

@article{bb384879,
        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#TT378960"}

@article{bb384880,
        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#TT378961"}

@article{bb384881,
        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#TT378962"}

@article{bb384882,
        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#TT378963"}

@article{bb384883,
        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#TT378964"}

@article{bb384884,
        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#TT378965"}

@article{bb384885,
        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#TT378966"}

@article{bb384886,
        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#TT378967"}

@article{bb384887,
        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#TT378968"}

@article{bb384888,
        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#TT378969"}

@article{bb384889,
        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#TT378970"}

@article{bb384890,
        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#TT378971"}

@inproceedings{bb384891,
        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#TT378972"}

@inproceedings{bb384892,
        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#TT378973"}

@article{bb384893,
        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#TT378974"}

@article{bb384894,
        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#TT378975"}

@article{bb384895,
        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#TT378976"}

@article{bb384896,
        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#TT378977"}

@article{bb384897,
        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#TT378978"}

@article{bb384898,
        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#TT378979"}

@article{bb384899,
        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#TT378980"}

Last update:Aug 19, 2026 at 13:26:35