Evaluation of Spoken Language Recognition Systems: Phonotactic approaches, backend and fussion

824 visualizacións 4 de xul. de 2013

In the introductory talk, we first aim to make the students understand the task of spoken language recognition (SLR) as defined in NIST and Albayzin evaluations. Then we will introduce different approaches to SLR ---which are classified either as acoustic or phonotactic, depending on the relying features---, from those applied in the nineties of the last century (GMM-UBM and PPRLM approaches) to the most successful state-of-the-art technologies (Phone-Lattice-SVM and MFCC-SDC-iVector approaches). The third part of the talk will deal with the backend and fusion models typically applied to combine different systems and get improved performance. Finally, we will describe the three Albayzin Language Recognition Evaluations (LRE) carried out in 2008, 2010 and 2012, emphasizing the differences among them and with regard to NIST LRE, and focusing on the conditions, datasets and evaluation measure defined for the Albayzin 2012 LRE, which will be used as benchmark in the practice session.

Luis Javier Rodríguez Fuentes
Software Technologies Working Group (GTTS), Department of Electricity and Electronics (ZTF-FCT), University of the Basque Country (UPV/EHU)
Mikel Penagarikano
Software Technologies Working Group (GTTS), Department of Electricity and Electronics (ZTF-FCT), University of the Basque Country (UPV/EHU)

Benvida

Edita de Lorenzo - Directora da Escola Escola de Enxeñaría de Telecomunicación

Emotional Speech Systems: What is an emotional system?

Juan Manuel Montero Martínez - Speech Technology Group (GTH), Department of Electronic Engineering (IEL)

Introduction to Audio Segmentation and Classification

Laura Docio Fernández - Multimedia Technologies Group (GTM), AtlantTIC Research Center

Implementation of Segmentation and Classification at the Same Time

Laura Docio Fernández - Multimedia Technologies Group (GTM), AtlantTIC Research Center

An Overview of the NIST Series of Speaker Recognition Evaluations and Technologies

Joaquin González-Rodríguez - Biometric Recognition Group – ATVS, Escuela Politécnica Superior

Session Variability Compensation in Speaker Recognition

Javier Gonzalez-Dominguez - Biometric Recognition Group – ATVS, Escuela Politécnica Superior

Speech technologies: research opportunities at Vicomtech-IK4

Arantza del Pozo - Head of the Human Speech and Language Technology Group

Evaluation of Spoken Language Recognition Systems: Tasks, applications, general issues and acoustic approaches

Luis Javier Rodríguez Fuentes - Software Technologies Working Group (GTTS), Department of Electricity and Electronics (ZTF-FCT)

Evaluation of Spoken Language Recognition Systems: Phonotactic approaches, backend and fussion

Luis Javier Rodríguez Fuentes - Software Technologies Working Group (GTTS), Department of Electricity and Electronics (ZTF-FCT)