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

Project description

An optimised automatic speaker recognition technology

Speech recognition is central to a broad spectrum of applications. The growing development of data exploitation and analysis techniques offers solutions for continuous improvement in the speech-processing industry. The EU-funded ETE SPEAKER project aims to develop an innovative tool based on automatic speaker recognition (SID) that isolates the necessary information to determine the identity of the speaker in a speech recording. ETE SPEAKER will focus on fully investigating and utilising the potential of deep neural networks to disentangle the speaker-specific information from the rest of nuisance variability. Its main aim is the introduction of an end-to-end SID conform to the latest Speaker Recognition Evaluation standards.

Fields of science

• natural sciences › computer and information sciences › artificial intelligence › machine learning › deep learning
• natural sciences › computer and information sciences › artificial intelligence › computational intelligence

Programme(s)

• H2020-EU.1.3. - EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions Main Programme
• H2020-EU.1.3.2. - Nurturing excellence by means of cross-border and cross-sector mobility

Topic(s)

• MSCA-IF-2018 - Individual Fellowships

Call for proposal

H2020-MSCA-IF-2018

See other projects for this call

Funding Scheme

MSCA-IF-EF-ST - Standard EF

Coordinator

VYSOKE UCENI TECHNICKE V BRNE

Net EU contribution

€ 120 817,20

Address

Antoninska 548/1
601 90 Brno Stred
Czechia

Region

Jihovýchod › Jihomoravský kraj

Activity type

Higher or Secondary Education Establishments

Links

Other funding

€ 0,00