Speech recognition method, device and equipment and storable medium

The invention provides a speech recognition method and device, equipment and a storable medium, and relates to the technical field of artificial intelligence, in particular to the field of speech recognition. The method comprises the steps that an acoustic model is trained in an adversarial multi-task training mode, a network structure comprises a feature extraction network, a voice recognition network and a domain classification network, firstly, voice data in a non-echo scene is collected to serve as voice sample data of a source domain, and voice data in an echo scene is collected to serve as voice sample data of a target domain; training a voice recognition network by using the voice sample data of the source domain, and training a feature extraction network and a domain classification network which have an adversarial relationship by using the voice sample data of the source domain and the voice sample data of the target domain, so that features extracted by the feature extraction network are features wh