US 11,749,259 B2
Proper noun recognition in end-to-end speech recognition
Charles Caleb Peyser, New York, NY (US); Tara N. Sainath, Jersey City, NJ (US); and Golan Pundak, New York, NY (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jan. 15, 2021, as Appl. No. 17/150,491.
Claims priority of provisional application 62/966,823, filed on Jan. 28, 2020.
Prior Publication US 2021/0233512 A1, Jul. 29, 2021
Int. Cl. G10L 15/06 (2013.01); G10L 15/16 (2006.01); G10L 15/18 (2013.01); G10L 15/187 (2013.01); G06N 3/049 (2023.01)
CPC G10L 15/063 (2013.01) [G06N 3/049 (2013.01); G10L 15/16 (2013.01); G10L 15/187 (2013.01); G10L 15/1815 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method that when executed on data processing hardware causes the data processing to perform operations comprising:
training a speech recognition model with a minimum word error rate loss function by:
receiving a training example comprising a ground-truth transcription, the ground-truth transcription comprising a word sequence that includes a proper noun;
generating a plurality of hypotheses corresponding to the training example, each hypothesis of the plurality of hypotheses comprising a respective sequence of words and a corresponding probability that indicates a likelihood that the hypothesis correctly identifies the ground-truth transcription;
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 exceeds a value assigned to a probability threshold; and
the respective sequence of words of the associated hypothesis does not include the proper noun; and
applying a penalty to the minimum word error rate loss function based on the corresponding probability associated with the one of the plurality of hypotheses satisfying the penalty criteria.