Patent attributes
Techniques for identifying and correcting synchronization errors between audio and subtitles for media content are described herein. For example, a portion of a subtitle file associated with media content may be extracted based on subtitle cues included in the portion of the subtitle file. In embodiments, an audio to text file may be generated from the extracted portion using a speech to text algorithm. A detected subtitle text file may be generated using the subtitle file, the audio to text file, and an edit distance algorithm. In embodiments, one or more synchronization errors between the audio and subtitles for the media content may be identified based on time stamp information associated with the audio to text file and a subtitle cue for the extracted portion of the subtitle file.