CPC G10L 15/08 (2013.01) [G06F 16/685 (2019.01); G10L 15/1815 (2013.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01); G10L 21/0272 (2013.01); G10L 25/48 (2013.01); H04M 3/4936 (2013.01); G10L 2015/225 (2013.01); G10L 21/0208 (2013.01); H04M 2201/40 (2013.01); H04M 2203/352 (2013.01)] | 20 Claims |
1. A computer-implemented method executed on data processing hardware that causes the data processing hardware to perform operations comprising:
receiving first audio data and second audio data captured by a computing device associated with a user;
processing the first audio data to identify an entity associated with the first audio data;
retrieving a set of terms related to the identified entity;
influencing, using the retrieved set of terms related to the identified entity, a speech recognition language model; and
generating, using the influenced speech recognition language model, a transcription of the second audio data.
|