Wipro Limited
System and method for text to speech conversion of an electronic document

Abstract:

The present disclosure relates to methods, non-transitory computer readable media, and devices for text-to-speech conversion of electronic documents. An electronic document comprising one or more pages comprising a plurality of characters and a plurality of first segments is received. The plurality of characters is segmented into a plurality of second segments based on first metadata associated with the plurality of characters. A first relationship between each of the plurality of second segments is identified based on the first metadata associated with the plurality of characters, second metadata associated with the plurality of first segments, and spatial information associated with the plurality of segments. A reading sequence of the electronic document is determined based on the first relationship. An audio is then generated based on the reading sequence of the electronic document.