Robust End-To-End SPEAKER recognition based on deep learning and attention models

Descripción del proyecto

Una tecnología optimizada para el reconocimiento automático del locutor

El reconocimiento de voz es fundamental en una amplia gama de aplicaciones. El creciente desarrollo de las técnicas de análisis y explotación de datos ofrece innovaciones para la mejora continua de la industria del procesamiento de voz. El proyecto ETE SPEAKER, financiado con fondos europeos, se propone desarrollar una herramienta innovadora basada en el reconocimiento automático del locutor (RAL) que aísla la información necesaria para determinar la identidad del locutor en una grabación de voz. ETE SPEAKER se centrará en investigar y utilizar plenamente el potencial de las redes neuronales profundas para desentrañar la información propia del locutor del resto de la variabilidad molesta. Su objetivo principal es la introducción del RAL de extremo a extremo conforme a las últimas normas de evaluación de reconocimiento del locutor.

Objetivo

This project focuses on automatic speaker recognition (SID), the task of determining the identity of the speaker in a speech recording. Disentangling the speaker specific information from the rest of nuisance variability requires complex models. Deep neural networks (DNNs) have recently showed their potential for this, as the popular x-vector learnt by a DNN.
Here, we aim for end-to-end SID where the system is optimized as a whole for the target task. Despite several attempts in this line of research, many aspects still remain unexplored or not explored thoroughly.
We also propose to explore recurrent approaches, suitable for dealing with temporal signals, as well as different pooling methods to obtain a fixed-length representation from a variable length input sequence of speech features.
Next, we want to explore different flavors of attention mechanisms, which make the DNN to focus on relevant parts of the input, providing a way to quantify how much evidence has been collected about the speaker identity and the uncertainty of the obtained representation, which is a critical issue when making (Bayesian) decisions in SID.
Finally, some other approaches such as using the raw signal (instead of features) or other advances that might arise will be also explored for SID and related tasks.
To achieve our goals, we will start from theory, implement the proposed approaches and test on public SID benchmarks such as NIST SREs. The outcomes are intended to benefit both scientific community and speech processing industry.
The applicant Dr. Alicia Lozano-Diez is an excellent female researcher, who has done her Ph.D. at Audias (Universidad Autonoma de Madrid, Spain), a respected research lab. The host group Speech@FIT from Brno University of Technology (Czechia) has a top-class track on speech processing research. Thus, we expect the combination of both the researcher and the host to boost the researcher career and benefit the host group (and its industrial European partners).

Ámbito científico

Programa(s)

Tema(s)

MSCA-IF-2018 - Individual Fellowships

Convocatoria de propuestas

H2020-MSCA-IF-2018

Consulte otros proyectos de esta convocatoria

Régimen de financiación

MSCA-IF-EF-ST - Standard EF

Coordinador

VYSOKE UCENI TECHNICKE V BRNE

Aportación neta de la UEn

€ 120 817,20

Dirección

ANTONINSKA 548/1
601 90 Brno Stred
Chequia

Región

Česko Jihovýchod Jihomoravský kraj

Tipo de actividad

Higher or Secondary Education Establishments

Enlaces

Contactar con la organización Sitio web

Participación en los programas de I+D de la UE

Red de colaboración de HORIZON

Coste total