Large margin training for attention-based end-to-end speech recognition
AssigneeTencent America LLC
InventorsPeidong WANG, Jia CUI, Chao WENG, Dong YU
Life of this patent
Estimating the term…
Loading patent…
AssigneeTencent America LLC
InventorsPeidong WANG, Jia CUI, Chao WENG, Dong YU
Estimating the term…
A method of attention-based end-to-end (E2E) automatic speech recognition (ASR) training, includes performing cross-entropy training of a model, based on one or more input features of a speech signal, performing beam searching of the model of which the cross-entropy training is performed, to generate an n-best hypotheses list of output hypotheses, and determining a one-best hypothesis among the generated n-best hypotheses list. The method further includes determining a character-based gradient and a word-based gradient, based on the model of which the cross-entropy training is performed and a loss function in which a distance between a reference sequence and the determined one-best hypothesis is maximized, and performing backpropagation of the determined character-based gradient and the determined word-based gradient to the model, to update the model.
A method of attention-based end-to-end (E2E) automatic speech recognition (ASR) training, the method comprising:
An apparatus for attention-based end-to-end (E2E) automatic speech recognition (ASR) training, the apparatus comprising:
A non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a device, cause the at least one processor to:
Dependencies are inferred from the claim text.