20240054995. INPUT-AWARE AND INPUT-UNAWARE ITERATIVE SPEECH RECOGNITION simplified abstract (Verint Americas Inc.)

From WikiPatents
Jump to navigation Jump to search

INPUT-AWARE AND INPUT-UNAWARE ITERATIVE SPEECH RECOGNITION

Organization Name

Verint Americas Inc.

Inventor(s)

Michael Levy of Alpharetta GA (US)

Jay Miller of Alpharetta GA (US)

INPUT-AWARE AND INPUT-UNAWARE ITERATIVE SPEECH RECOGNITION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240054995 titled 'INPUT-AWARE AND INPUT-UNAWARE ITERATIVE SPEECH RECOGNITION

Simplified Explanation

The abstract describes an interactive voice response (IVR) system that utilizes iterative speech recognition with semantic interpretation. This system optimizes computing resources and enables low-latency discovery of start-of-speech events, which can be used for operations like barge-in. The IVR system receives audio input and applies an input-aware recognition process. Upon generating a start-of-speech event, it applies an input-unaware recognition process to the remaining audio input and determines the semantic meaning.

  • The IVR system includes iterative speech recognition with semantic interpretation.
  • It conserves computing resources and facilitates low-latency discovery of start-of-speech events.
  • The system can repeatedly receive and process audio input.
  • It applies an input-aware recognition process to the audio input.
  • Upon generating a start-of-speech event, it applies an input-unaware recognition process to the remaining audio input.
  • The system determines the semantic meaning of the relevant portion of the audio input.

Potential applications of this technology:

  • Interactive voice response systems for customer support or information retrieval.
  • Voice-controlled virtual assistants or smart home devices.
  • Speech-to-text transcription services.
  • Call center automation.

Problems solved by this technology:

  • Optimizes and conserves computing resources by applying input-aware and input-unaware recognition processes.
  • Enables low-latency discovery of start-of-speech events, improving responsiveness and facilitating operations like barge-in.
  • Provides semantic interpretation of audio input, enhancing the understanding and processing of spoken commands or queries.

Benefits of this technology:

  • Improved efficiency and resource utilization in speech recognition systems.
  • Enhanced user experience through low-latency response and accurate semantic interpretation.
  • Enables seamless integration of voice control in various applications and devices.
  • Facilitates automation and streamlines processes in call centers or customer support systems.


Original Abstract Submitted

an interactive voice response (ivr) system including iterative speech recognition with semantic interpretation is deployed to process an audio input in a manner that optimizes and conserves computing resources and facilitates low-latency discovery of start-of-speech events that can be used to support external processes such as barge-in operations. the ivr system can repeatedly receive an audio input at a speech processing component and apply an input-aware recognition process to the audio input. in response to generating a start-of-speech event, the ivr system can apply an input-unaware recognition process to the remaining audio input and determine a semantic meaning in relation to the relevant portion of the audio input.