| CPC G06F 16/383 (2019.01) [G06F 16/335 (2019.01); G06F 16/35 (2019.01); G06F 16/685 (2019.01); G06F 16/7844 (2019.01); G06F 30/27 (2020.01); G06F 40/00 (2020.01); G10L 15/00 (2013.01)] | 20 Claims |

|
1. A method comprising:
obtaining, by a computing system, a text representation of a podcast episode and an audio representation of the podcast episode;
obtaining, by the computing system, person data defining a list of person names;
correlating, by the computing system, the person data with the text representation of the podcast episode, to find a match between (i) a person name from the list of the person names and (ii) a text string in the text representation of the podcast episode;
obtaining, by the computing system, at least one or more reference voice templates of a voice of a person having the person name;
using, by the computing system, voice identification, including matching the audio representation of the podcast episode against the one or more voice templates, to detect presence in the podcast episode of the voice of the person having the person name;
based at least on the detecting in the podcast episode of the voice of the person having the person name, generating, by the computing system, metadata that associates the person name with the podcast episode; and
outputting, by the computing system, the generated metadata.
|