摘要 |
Provided are a method and an apparatus for producing a descriptive video service using text-to-speech (TTS). The apparatus for producing a descriptive video service comprises a mute section detecting unit analyzing an audio signal of content to detect a mute section from the audio signal, a descriptive section selecting unit selecting a section into which description is to be inserted, from the detected mute section, and a description inserting unit inserting a description to the selected section using TTS. |