Abstract: Techniques for automatic subtitle enabling are described herein. In various embodiments, one or more servers, which include processor(s) and non-transitory memory, receive an audio file and a subtitle file of a media content object, obtain, using speech-to-text, transcription of the audio file and one or more confidence scores for one or more portions of the transcription. The server(s) then determine one or more similarity scores representing similarities between the one or more portions of the transcription and one or more corresponding portions in the subtitle file, and derive a clarity score for each of the one or more portions in the subtitle file based on the one or more similarity scores and the one or more confidence scores, wherein when playing the media content object, display of each of the one or more corresponding portions in the subtitle file is enabled based at least in part on the clarity score.

Abstract: Techniques for automatic subtitle enabling are described herein. In various embodiments, one or more servers, which include processor(s) and non-transitory memory, receive an audio file and a subtitle file of a media content object, obtain, using speech-to-text, transcription of the audio file and one or more confidence scores for one or more portions of the transcription. The server(s) then determine one or more similarity scores representing similarities between the one or more portions of the transcription and one or more corresponding portions in the subtitle file, and derive a clarity score for each of the one or more portions in the subtitle file based on the one or more similarity scores and the one or more confidence scores, wherein when playing the media content object, display of each of the one or more corresponding portions in the subtitle file is enabled based at least in part on the clarity score.