Voice interaction method, device, equipment, medium and program product

By determining the confidence of the original signal and the speech enhancement signal in the voice interaction system and performing weighted summing to determine the target signal, the speech distortion problem caused by the speech enhancement technology under low signal-to-noise ratio conditions is solved, and the accuracy of speech interaction and the stability of the system is improved.

CN119943071AActive Publication Date: 2025-05-06IFLYTEK CO LTD
15 Cites 0 Cited by

Patent Information

Application Number
CN202510063415.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-15
Publication Date
2025-05-06
Estimated Expiration
2045-01-15

Smart Images

  • Figure CN119943071A_ABST
    Figure CN119943071A_ABST
Patent Text Reader

Abstract

The invention provides a voice interaction method and device, equipment, a medium and a program product. The voice interaction method comprises the following steps: determining a first confidence coefficient of a first original signal and a second confidence coefficient of a first voice enhancement signal; wherein the first voice enhancement signal is a signal obtained by performing voice enhancement on the first original signal; determining a target signal based on the first confidence coefficient, the second confidence coefficient, the second original signal and the second speech enhancement signal; wherein the second voice enhancement signal is a signal obtained by performing voice enhancement on a second original signal; and performing voice interaction with the target device based on the target signal. According to the invention, voice distortion caused by voice enhancement can be reduced.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Voice object recognition method and device

    CN109427336A

  • Sound mixing method and device, terminal and readable storage medium

    CN110060696A

  • Speech enhancement method, device and equipment and readable storage medium

    CN110808058A

  • Audio signal processing method and electronic equipment

    CN111477243A

  • Voice recognition method and device, electronic equipment and storage medium

    CN111696532A