Proper Noun Recognition in End-to-End Speech Recognition
AssigneeGoogle Inc.
InventorsCharles Caleb Peyser, Tara N. Sainath, Golan Pundak
Life of this patent
Estimating the term…
Loading patent…
AssigneeGoogle Inc.
InventorsCharles Caleb Peyser, Tara N. Sainath, Golan Pundak
Estimating the term…
A method for training a speech recognition model with a minimum word error rate loss function includes receiving a training example comprising a proper noun and generating a plurality of hypotheses corresponding to the training example. Each hypothesis of the plurality of hypotheses represents the proper noun and includes a corresponding probability that indicates a likelihood that the hypothesis represents the proper noun. The method also includes determining that the corresponding probability associated with one of the plurality of hypotheses satisfies a penalty criteria. The penalty criteria indicating that the corresponding probability satisfies a probability threshold, and the associated hypothesis incorrectly represents the proper noun. The method also includes applying a penalty to the minimum word error rate loss function.
A computer-implemented method that when executed on data processing hardware causes the data processing to perform operations comprising:
A system comprising:
Dependencies are inferred from the claim text.