Voice directional recognition interaction method and device, equipment and medium

An interactive method and voice technology, applied in voice recognition, voice analysis, special data processing applications, etc., can solve problems such as environmental noise, voice control device recognition effect interference, etc., to achieve the effect of eliminating interference and increasing anthropomorphic effects

Active Publication Date: 2019-08-30
浙江小远机器人有限公司
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this patent still does not solve the interference of environmental noise. When multiple sound sources appear within the 360-degree range of the voice control device, such as when the image receiving unit recognizes a human face and receives multiple voice signals around the voice control device, the voice control The recognition effect of the device will be interfered by the external environment sound

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
  • Voice directional recognition interaction method and device, equipment and medium
  • Voice directional recognition interaction method and device, equipment and medium
  • Voice directional recognition interaction method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Voice directional recognition interaction method, through directional acquisition of voice signals and face images that meet the requirements, for voice interaction, such as figure 1 shown, including the following steps:

[0036] Obtain the collected voice text content;

[0037] Obtain a face image that satisfies both the image acquisition angle and the acquisition distance;

[0038] According to the obtained voice text content and face image, judge whether to make a reply;

[0039] Wherein, the image collection angle is 60-70 degrees, and the collection distance is less than or equal to 1 m.

[0040] Moreover, the method for collecting the above-mentioned speech and text content is: performing speech recognition after performing directional pickup and signal enhancement on the sound signal directly in front.

[0041] When the voice text content and the face image are obtained at the same time, a reply is made to the voice text content, otherwise no reply is made.

...

Embodiment 2

[0078] This embodiment discloses a device corresponding to the voice orientation recognition interaction method in Embodiment 1, please refer to figure 2 shown, including:

[0079] The voice pickup device 210 is used for directional picking up the sound signal directly ahead, and performing voice recognition to obtain the voice text content;

[0080] The image acquisition device 220 is preset with an image acquisition angle and an acquisition distance, and acquires a face image that satisfies both the image acquisition angle and the acquisition distance;

[0081] The processing unit 230 is configured to acquire the voice text content and the face image, and determine whether to make a reply.

[0082] In this embodiment, the voice pickup device 210 is a fixedly installed non-steerable array microphone. The setting method of the array microphone is to adjust the range of the directional microphone beam to the front, and the angle is controlled between 60-70 degrees. The sound...

Embodiment 3

[0085] image 3 A schematic diagram of the electronic device provided by Embodiment 3 of the present invention, such as image 3 As shown, the electronic device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in a computer device may be one or more, image 3 Take a processor 310 as an example; the processor 310, memory 320, input device 330 and output device 340 in the electronic device can be connected by bus or other methods, image 3 Take connection via bus as an example.

[0086] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and modules, such as program instructions / modules corresponding to the voice-directed recognition interaction method in the embodiment of the present invention (for example, a voice-oriented recognition interaction device in the processing unit 230). The processor 310 executes various functional applicatio...

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 the field of man-machine voice interaction, and discloses a voice directional recognition interaction method. The voice directional recognition interaction method comprises the following steps: picking up a forward voice signal for recognition to obtain voice text content, and obtaining the voice text content; based on an image acquisition angle and an acquisition distance, obtaining a face image meeting the image acquisition angle and the acquisition distance at the same time; and judging whether a reply is made or not according to the voice text content and the faceimage, wherein the image acquisition angle is 60 degrees, and the acquisition distance is less than or equal to 1m. The invention further discloses a voice directional recognition interaction device,electronic equipment and a computer storage medium. The voice directional recognition interaction method conforms to the daily communication habit, can effectively eliminate the sound of foreign people and the sound of the environment, and achieves effective personified communication with a user who is interacting in front.

Description

technical field [0001] The invention relates to the field of human-machine voice interaction, in particular to a voice orientation recognition interaction method, device, equipment and medium. Background technique [0002] At present, the application of robots or voice assistants is generally in complex environments, such as conference rooms, outdoors, shopping malls and other noisy environments, which will cause various problems such as noise, reverberation, human voice interference, echo, etc., and in the process of human-computer voice interaction In , the array microphone used for sound collection will also recognize sounds within a 360-degree range around it. In order to solve the problem of misrecognizing environmental sounds, the "wake-up word" technology is adopted in voice interaction. In practical applications, the voice content will be recognized only after the robot or voice interaction assistant receives the wake word; otherwise, no recognition will be performed...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G10L15/26G10L21/0208
CPCG06F16/3329G10L15/26G10L21/0208
Inventor 嵇望汪斌林达李林峰
Owner 浙江小远机器人有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products