Patents by Inventor E Santhosh Kumar

E Santhosh Kumar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Expressive text-to-speech utilizing contextual word-level style tokens
    Patent number: 11322133
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate expressive audio for input texts based on a word-level analysis of the input text. For example, the disclosed systems can utilize a multi-channel neural network to generate a character-level feature vector and a word-level feature vector based on a plurality of characters of an input text and a plurality of words of the input text, respectively. In some embodiments, the disclosed systems utilize the neural network to generate the word-level feature vector based on contextual word-level style tokens that correspond to style features associated with the input text. Based on the character-level and word-level feature vectors, the disclosed systems can generate a context-based speech map. The disclosed systems can utilize the context-based speech map to generate expressive audio for the input text.
    Type: Grant
    Filed: July 21, 2020
    Date of Patent: May 3, 2022
    Assignee: Adobe Inc.
    Inventors: Sumit Shekhar, Gautam Choudhary, Abhilasha Sancheti, Shubhanshu Agarwal, E Santhosh Kumar, Rahul Saxena
  • EXPRESSIVE TEXT-TO-SPEECH UTILIZING CONTEXTUAL WORD-LEVEL STYLE TOKENS
    Publication number: 20220028367
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate expressive audio for input texts based on a word-level analysis of the input text. For example, the disclosed systems can utilize a multi-channel neural network to generate a character-level feature vector and a word-level feature vector based on a plurality of characters of an input text and a plurality of words of the input text, respectively. In some embodiments, the disclosed systems utilize the neural network to generate the word-level feature vector based on contextual word-level style tokens that correspond to style features associated with the input text. Based on the character-level and word-level feature vectors, the disclosed systems can generate a context-based speech map. The disclosed systems can utilize the context-based speech map to generate expressive audio for the input text.
    Type: Application
    Filed: July 21, 2020
    Publication date: January 27, 2022
    Inventors: Sumit Shekhar, Gautam Choudhary, Abhilasha Sancheti, Shubhanshu Agarwal, E Santhosh Kumar, Rahul Saxena