公开(公告)号：US20220319525A1

公开(公告)日：2022-10-06

申请号：US17708738

申请日：2022-03-30

Applicant: Jio Platforms Limited

Inventor： Venkateshwaran MAHADEVAN ,  Bhupendra SINHA ,  Gaurav DUGGAL ,  Sameer MEHTA ,  Manoj Kumar GARG

IPC: G10L19/005 ,  G10L25/18 ,  G10L25/21 ,  G10L19/02

Abstract: The present disclosure relates to a system and method for facilitating error-free communication of data by enabling transfer of data over audio signal in near-ultra sonic frequencies with specially designed audio emitted using a mixture of frequencies to achieve maximum stability. The method may include randomized emission of data bits over a plurality of frequency ranges to allow temporal and frequency voting. The audio signal transmitted may be received by pre-processing the received audio signal to remove unused frequency bands and unwanted audio artifacts introduced during transmission. The pre-processed audio signal may be further applied with a plurality of audio processing levels to denoise, smoothen the audio signal by going through noise subtraction using unique noise profiles and spectrally gate using curated thresholds. The audio signal may be then demodulated using a unique confidence score based on the power of all the frequencies emitted to find the data transmitted.

公开(公告)号：US20220215834A1

公开(公告)日：2022-07-07

申请号：US17566966

申请日：2021-12-31

Applicant: JIO PLATFORMS LIMITED

Inventor： Gaurav DUGGAL ,  Arijay CHAUDHRY ,  Paras AHUJA ,  Anil Kumar GOYAL ,  Venkateshwaran MAHADEVAN

IPC: G10L15/197 ,  G10L15/16 ,  G10L15/22 ,  G10L25/18 ,  G06F40/58

Abstract: The present invention relates to a system and a method for enabling automatic conversion of speech input to text. The implementation involves receiving an audio file pertaining to speech of a user, extracting a first set of attributes indicative of plurality of time frames spaced along the duration of the audio file, extracting a second set of attributes indicative of speech patterns, predicting a first set of characters to generate a first output sentence, determining, through an AI engine, a first data set comprising a corpus of sentences of a predefined language based on a predefined language usage parameters and generating a textual output in the predefined language based on a combination of said extraction, said prediction and said AI engine based determination.