El método presentado en la clase anterior
Lindley, D.V., 1977. A problem in forensic science. Biometrika 64/2, 207–213
Pero en realidad hay varias alternativas...
Rose, Phil. "Technical forensic speaker recognition: Evaluation, types and testing of evidence." Computer Speech & Language 20.2 (2006): 159-191.
Nos sirve para analizar a las grabaciones
Rose, Phil. "Technical forensic speaker recognition: Evaluation, types and testing of evidence." Computer Speech & Language 20.2 (2006): 159-191.
Rose, Phil. Forensic speaker identification. CRC Press, 2003.
Rose, Phil. Forensic speaker identification. CRC Press, 2003.
Rose, Phil. Forensic speaker identification. CRC Press, 2003.
Kinoshita, Y., & Osanai, T. (2006, December). Within speaker variation in diphthongal dynamics: What can we compare. In Proceedings of the 11th Australasian International Conference on Speech Science & Technology, Auckland, New Zealand. Australia: Australasian Speech Science & Technology Association, Canberra (pp. 112-117).
Likelihood-ratio forensic voice comparison using parametric representations of the formant trajectories of diphthongsa) Morrison, Geoffrey Stewart, The Journal of the Acoustical Society of America, 125, 2387-2397 (2009)
Likelihood-ratio forensic voice comparison using parametric representations of the formant trajectories of diphthongsa) Morrison, Geoffrey Stewart, The Journal of the Acoustical Society of America, 125, 2387-2397 (2009)
Likelihood-ratio forensic voice comparison using parametric representations of the formant trajectories of diphthongsa) Morrison, Geoffrey Stewart, The Journal of the Acoustical Society of America, 125, 2387-2397 (2009)
Rose, Phil. Forensic speaker identification. CRC Press, 2003.
Rose, Phil. Forensic speaker identification. CRC Press, 2003.
Se comprime la señal en ventanas
Con la representación creamos modelos
Rose, P. (2006) Catching criminals by their voice: Combining automatic and traditional methods for optimum performance in forensic speaker recognition.
Gausian Mixture Models (GMM)
Meuwly, Didier, and Andrzej Drygajlo. "Forensic speaker recognition based on a Bayesian framework and Gaussian Mixture Modelling (GMM)." 2001: A Speaker Odyssey-The Speaker Recognition Workshop. 2001.
Meuwly, Didier, and Andrzej Drygajlo. "Forensic speaker recognition based on a Bayesian framework and Gaussian Mixture Modelling (GMM)." 2001: A Speaker Odyssey-The Speaker Recognition Workshop. 2001.
Aprendizaje profundo
Lee, Honglak, et al. "Unsupervised feature learning for audio classification using convolutional deep belief networks." Advances in neural information processing systems. 2009.
Joaquin Gonzalez-Rodriguez, Andrzej Drygajlo, Daniel Ramos-Castro, Marta Garcia-Gomar, Javier Ortega-Garcia, Robust estimation, interpretation and assessment of likelihood ratios in forensic speaker recognition, Computer Speech & Language, Volume 20, Issues 2–3, April–July 2006, Pages 331-355, ISSN 0885-2308