Adaptive decoding method and device, computer equipment and storage medium

A decoding method and self-adaptive technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as too small overlapping of sliding windows, too large overlapping of sliding windows, etc., to avoid excessively large or too small overlapping of sliding windows, The effect of reducing the number of times of decoding and processing time and reducing the possibility of voice information loss

CN114783438AActive Publication Date: 2022-07-22深圳市友杰智新科技有限公司
13 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-07-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides an adaptive decoding method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining voice data, and carrying out the preprocessing of the voice data, and obtaining a decoding matrix; and performing sliding window processing on the decoding matrix according to a self-adaptive step length strategy, and outputting a decoding result when the confidence coefficient of a keyword appearing in a sliding window meets a preset threshold value. The sliding window processing is carried out on the decoding matrix according to the self-adaptive step length strategy, so that the step length of each sliding window is changed, the problem that the sliding windows are overlapped too large or too small is avoided, and the possibility of voice information loss is reduced while the decoding frequency and the processing time are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of speech recognition, and in particular, to an adaptive decoding method, apparatus, computer equipment and storage medium. Background technique

[0002] Wake word and command word recognition belong to the field of speech recognition and are widely used in scenarios such as smart homes and smart terminals. When the existing wake word and command word models are applied, the user's voice is detected in real time, and feedback is given when a specific word is detected. How to accurately detect specific words in streaming speech data is not only related to the performance of the algorithm, but also the algorithm of streaming processing. For example, common stream processing will select a fixed window length, and then slide according to a certain step size. When the sliding processing method is performed according to a certain step size, if the overlapping of the sliding windows is too large, the numb...

Examples

Embodiment Construction

[0041] It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] refer to figure 1 , an adaptive decoding method according to an embodiment of the present invention, comprising:

[0044] S1, acquire voice data, and perform preprocessing on the voice data to obtain a decoding matrix;

[0045] S2. Perform sliding window processing...