17951585. DEVICE AND METHOD WITH TARGET SPEAKER IDENTIFICATION simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

From WikiPatents
Jump to navigation Jump to search

DEVICE AND METHOD WITH TARGET SPEAKER IDENTIFICATION

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Kai Wang of Xi'an (CN)

Xiaolei Zhang of Xi'an (CN)

Miao Zhang of Xi'an (CN)

DEVICE AND METHOD WITH TARGET SPEAKER IDENTIFICATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17951585 titled 'DEVICE AND METHOD WITH TARGET SPEAKER IDENTIFICATION

Simplified Explanation

The abstract of the patent application describes a method implemented by a processor for determining whether a target speaker corresponds to a user based on voice features. The method involves extracting voice features from the input voice of the target speaker, determining the utterance scenario based on these features, generating a final target speaker voice feature, and comparing it with a final user voice feature to determine if they correspond.

  • The method extracts voice features from the input voice of a target speaker.
  • It determines the utterance scenario of the input voice, which can be either a single-speaker scenario or a multiple-speaker scenario.
  • Based on the determined utterance scenario, a final target speaker voice feature is generated.
  • The final target speaker voice feature is compared with a final user voice feature to determine if the target speaker corresponds to the user.

Potential Applications

  • Speaker recognition systems for authentication purposes.
  • Voice-controlled devices that can differentiate between different users.
  • Call center systems that can identify and authenticate callers based on their voice.

Problems Solved

  • The method solves the problem of determining whether a target speaker corresponds to a user based on their voice features.
  • It addresses the challenge of differentiating between single-speaker and multiple-speaker scenarios in voice analysis.

Benefits

  • Improved accuracy in determining if a target speaker corresponds to a user.
  • Enhanced security in speaker recognition systems.
  • Increased usability and personalization in voice-controlled devices.


Original Abstract Submitted

A processor-implemented method includes: extracting a target speaker voice feature based on an input voice of a target speaker; determining an utterance scenario of the input voice based on the target speaker voice feature; generating a final target speaker voice feature based on the determined utterance scenario; and determining whether the target speaker corresponds to a user based on the final target speaker voice feature and a final user voice feature, wherein the determined utterance scenario comprises either one of a single-speaker scenario and a multiple-speaker scenario.

Retrieved from "http://wikipatents.org/index.php?title=17951585._DEVICE_AND_METHOD_WITH_TARGET_SPEAKER_IDENTIFICATION_simplified_abstract_(SAMSUNG_ELECTRONICS_CO.,_LTD.)&oldid=21024"