17937198. SYSTEM AND METHOD FOR COMMAND FULFILLMENT WITHOUT WAKE WORD simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR COMMAND FULFILLMENT WITHOUT WAKE WORD

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Sivakumar Balasubramanian of Sunnyvale CA (US)

Gowtham Srinivasan of San Jose CA (US)

Srinivasa Rao Ponakala of Sunnyvale CA (US)

Vijendra Raj Apsingekar of San Jose CA (US)

Anil Sunder Yadav of San Jose CA (US)

SYSTEM AND METHOD FOR COMMAND FULFILLMENT WITHOUT WAKE WORD - A simplified explanation of the abstract

This abstract first appeared for US patent application 17937198 titled 'SYSTEM AND METHOD FOR COMMAND FULFILLMENT WITHOUT WAKE WORD

Simplified Explanation

The method described in the patent application involves using a frame-level detector model and a word-level verifier model to perform automatic speech recognition on audio input. Here is a simplified explanation of the abstract:

  • The method starts by obtaining an audio input.
  • The audio input is then provided to a frame-level detector model, which analyzes the input at the frame level and makes predictions.
  • The first output of the frame-level detector model includes these frame-level predictions associated with at least a portion of the audio input.
  • Next, at least one chunked audio frame is provided to a word-level verifier model.
  • The second output of the word-level verifier model includes word-level probabilities associated with the at least one chunked audio frame.
  • Based on these word-level probabilities, the method instructs the performance of automatic speech recognition on the audio input.

Potential applications of this technology:

  • Automatic speech recognition systems for transcription services.
  • Voice-controlled virtual assistants.
  • Speech-to-text conversion in communication devices.
  • Language learning tools with real-time feedback.

Problems solved by this technology:

  • Improves the accuracy and efficiency of automatic speech recognition.
  • Enables real-time transcription and translation services.
  • Reduces the need for manual transcription and data entry.

Benefits of this technology:

  • Faster and more accurate transcription of audio content.
  • Enhanced user experience in voice-controlled devices.
  • Increased accessibility for individuals with hearing impairments.
  • Improved efficiency in language learning and communication.


Original Abstract Submitted

A method comprises obtaining an audio input. The method also includes providing at least a portion of the audio input to a frame-level detector model. The method also includes obtaining a first output of the frame-level detector model including frame-level predictions associated with at least the portion of the audio input. The method also includes providing at least one chunked audio frame to a word-level verifier model. The method also includes obtaining a second output of the word-level verifier model including word-level probabilities associated with the at least one chunked audio frame. The method also includes instructing performance of automatic speech recognition on the audio input based on the word-level probabilities associated with the at least one chunked audio frame.

Retrieved from "http://wikipatents.org/index.php?title=17937198._SYSTEM_AND_METHOD_FOR_COMMAND_FULFILLMENT_WITHOUT_WAKE_WORD_simplified_abstract_(SAMSUNG_ELECTRONICS_CO.,_LTD.)&oldid=29167"