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

Method and device for voice identification

A technology for recognizing speech and speech frames, which is applied in the computer field and can solve problems such as slow command response speed

Pending Publication Date: 2019-05-03
APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If there is a long pause after saying "Call", if you want to adapt to this scene, you can only adjust and increase the waiting time of VAD tail point detection, but the increase of VAD tail point detection time will inevitably lead to "open The problem that the response speed of the "window" command slowed down

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
  • Method and device for voice identification
  • Method and device for voice identification
  • Method and device for voice identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present disclosure will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0031] It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

[0032] figure 1 An exemplary system architecture 100 is shown to which embodiments of the method for recognizing speech or the apparatus for recognizing speech of the present disclosure can be applied.

[0033] Such as figure 1 As shown, the system architecture 100 ma...

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 embodiment of the invention discloses a method and device for voice identification. A particular implementing mode of the method includes the steps that in response to a detected first voice framewith average energy greater than a preset starting point threshold, the first voice frame and voice frames after the first frame are sent to an identification engine in real time to obtain intermediate identification results of voice identification; in response to detected voice frames with average energy smaller than a preset end point threshold in the voice frames after the first frame, timingis started; if no voice frames with average energy greater than or equal to the preset end point threshold are detected within a preset end point overtime period, whether or not the intermediate identification results are matched with preset statement sets is detected; if the intermediate identification results are not matched with the preset statement sets, sending the voice frames to the identification engine is stopped, and the intermediate identification results serve as final results to be output. By adopting the implementing mode, the identification responding speed of voice with pausescan be increased.

Description

technical field [0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to methods and devices for recognizing speech. Background technique [0002] In a speech recognition application scenario, not every intention is a coherent sentence when expressed. Therefore, a general full-scenario endpoint detection algorithm cannot meet the actual needs of users, because for the same user, different intentions correspond to different speaking speeds and pause times. [0003] The existing technology usually divides the voice data by setting and adjusting the general parameters of voice endpoint detection, and then sends it to the voice engine. Under the balance of the two scenarios, a relatively balanced voice endpoint detection parameter value is selected to meet the interaction requirements of common scenarios. A balanced VAD (Voice Activity Detection, Voice Activity Detection) voice endpoint detection timeout parameter cannot sim...

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): G10L15/05G10L15/26G10L25/03
Inventor 贺学焱李俊博欧阳能钧
Owner APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD