Audio file annotation
AssigneeSap SE
InventorHans-Martin Ramsl
Life of this patent
Estimating the term…
Abstract
Text-to-speech translation is used to generate a transcript for an audio file. Text segments are associated with time segments in the transcript. A trained machine learning model determines, based on the text in the transcript, one or more topics for the audio file. The transcript is modified to include the determined one or more topics. A user interface may be presented that allows a user to search for portions of an audio file that relate to a particular topic. In response to the selected or entered topic, the user interface presents segments having a matching topic. The user may use voice or other user interface commands to modify the annotation of the audio file. User commands may also be used to extract data from the transcript and copy the data to a clipboard or to another application.
Claims20
A method comprising:
- accessing, by one or more processors, an annotation file for an audio file, the annotation file comprising a text transcription of the audio file;
- determining, by the one or more processors, based on the text transcription, a topic for each segment of a plurality of segments of a first predetermined length;
- determining, by the one or more processors, a confidence level of the topic for each segment of the plurality of segments;
- determining, by the one or more processors, a topic for each larger segment of a plurality of larger segments, each larger segment comprising a predetermined number of consecutive component segments of the plurality of segments, the determining of the topic for a larger segment based on the topics of the component segments and the confidence levels of the topics of the component segments;
- and
- modifying the annotation file to include the determined topics for the plurality of larger segments.
A system comprising:
- a memory that stores instructions;
- and
- one or more processors configured by the instructions to perform operations comprising:
- accessing an annotation file for an audio file, the annotation file comprising a text transcription of the audio file;
- determining based on the text transcription, a topic for each segment of a plurality of segments of a first predetermined length;
- determining a confidence level of the topic for each segment of the plurality of segments;
- determining a topic for each larger segment of a plurality of larger segments of a second predetermined length, each larger segment comprising a predetermined number of consecutive component segments of the plurality of segments, the determining of the topic for a larger segment based on the topics of the component segments and the confidence levels of the topics of the component segments;
- and
- modifying the annotation file to include the determined topics for the plurality of larger segments.
A non-transitory computer-readable medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
- accessing an annotation file for an audio file, the annotation file comprising a text transcription of the audio file;
- determining based on the text transcription, a topic for each segment of a plurality of segments of a first predetermined length;
- determining a confidence level of the topic for each segment of the plurality of segments;
- determining a topic for each larger segment of a plurality of larger segments of a second predetermined length, each larger segment comprising a predetermined number of consecutive component segments of the plurality of segments, the determining of the topic for a larger segment based on the topics of the component segments and the confidence levels of the topics of the component segments;
- and
- modifying the annotation file to include the determined topics for the plurality of larger segments.
Dependencies are inferred from the claim text.