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.