Feature and feature variant reconstruction for recurrent model accuracy improvement in speech recognition
AssigneeInternational Business Machines Corporation
InventorsGakuto Kurata, Kartik Audhkhasi
Life of this patent
Estimating the term…
Loading patent…
AssigneeInternational Business Machines Corporation
InventorsGakuto Kurata, Kartik Audhkhasi
Estimating the term…
A multi-task learning system is provided for speech recognition. The system includes a common encoder network. The system further includes a primary network for minimizing a Connectionist Temporal Classification (CTC) loss for speech recognition. The system also includes a sub network for minimizing a Mean squared error (MSE) loss for feature reconstruction. A first set of output data of the common encoder network is received by both of the primary network and the sub network. A second set of the output data of the common encode network is received only by the primary network from among the primary network and the sub network.
A multi-task learning system for speech recognition, comprising:
A computer-implemented method for speech recognition, comprising:
A computer program product for speech recognition, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
Dependencies are inferred from the claim text.