Multi-domain adversarial training of neural network acoustic models for distant speech recognition

Publication date: Available online 3 November 2018Source: Speech CommunicationAuthor(s): Seyedmahdad Mirsamadi, John H.L. HansenAbstractBuilding deep neural network acoustic models directly based on far-field speech from multiple recording environments with different acoustic properties is an increasingly popular approach to address the problem of distant speech recognition. The currently common approach to building such multi-condition (multi-domain) models is to compile available data from all different environments into a single train set, discarding information regarding the specific environment to which each utterance belongs. We propose a novel strategy for training neural network acoustic models based on adversarial training which makes use of environment labels during training. By ...

MedWorm Message: Have you tried our new medical search engine? More powerful than before. Log on with your social media account. 100% free.

from #Head and Neck by Sfakianakis via simeraentaxei on Inoreader https://ift.tt/2JGopqY