Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-label voice activity detection method and device and storage medium

A voice activity detection and multi-label technology, applied in voice analysis, instruments, etc., can solve the problems of poor robustness and low detection accuracy

Pending Publication Date: 2021-05-18
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a multi-label voice activity detection method, device, electronic equipment and computer-readable storage medium, the main purpose of which is to solve the problems of poor robustness and low detection accuracy in traditional voice activity detection methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-label voice activity detection method and device and storage medium
  • Multi-label voice activity detection method and device and storage medium
  • Multi-label voice activity detection method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0047] The invention provides a multi-label voice activity detection method. refer to figure 1 As shown, it is a schematic flowchart of a multi-label voice activity detection method provided by an embodiment of the present invention. The method may be performed by a device, and the device may be implemented by software and / or hardware.

[0048] In this embodiment, the multi-label voice activity detection method includes:

[0049] S110: Based on the preset noise seed model, determine the labeled noise data from the preset unlabeled data.

[0050] Wherein, based on the preset noise seed model, the step of determining the labeled noise data from the preset unlabeled data includes:

[0051] S111: Obtain training data including labeled and unlabeled noise seed models;

[0052] S112: Train a noise classification model ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to artificial intelligence, and discloses a multi-label voice activity detection method, which comprises the steps of determining labeled noise data from preset unlabeled data based on a preset noise seed model; determining noise containing feature data according to preset voice data, the preset unlabeled noise data and the labeled noise data; training a neural network model based on the noisy feature data until the neural network model is converged in a preset range, and forming a voice activity detection model; and detecting a to-be-detected voice signal based on the voice activity detection model to obtain an output tag corresponding to the to-be-detected voice signal. According to the invention, the voice activity detection efficiency and accuracy can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a multi-label voice activity detection method, device, electronic equipment and computer-readable storage medium. Background technique [0002] With the rapid development of artificial intelligence and computer technology, the artificial customer service telephone system of large enterprises has begun to be gradually upgraded to an intelligent customer service system. The voice dialogue system communicates with users to solve user problems, while reducing the labor cost of enterprise customer service and improving efficiency. . [0003] However, in the intelligent customer service voice dialogue system, the noise of various life scenes, including steady-state noise, impact noise, unsteady-state noise and non-coherent multi-person speaking interference noise, etc., has greatly affected the intelligent voice system. The accuracy of speech recognition in the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L25/78G10L25/30G10L25/51
CPCG10L25/78G10L25/30G10L25/51
Inventor 赵建平马骏王少军
Owner PING AN TECH (SHENZHEN) CO LTD