Voice data processing method and device

A voice data and processing method technology, applied in the field of data processing, can solve the problems of low cleaning efficiency of voice data and voice data, and achieve the effect of solving low cleaning efficiency and improving efficiency

Active Publication Date: 2016-08-17
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a voice data processing method and device, to at least solve the technical problem that the voice data cleaning efficiency is low due to the inability of the related technology to use the manual labeling method to clean the voice data

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 data processing method and device
  • Voice data processing method and device
  • Voice data processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] According to an embodiment of the present invention, a method embodiment of a voice data processing method is provided.

[0029] Optionally, in this embodiment, the above speech data processing method can be applied to figure 1 In the hardware environment constituted by the server 102 and the terminal 104 as shown. Such as figure 1 As shown, the server 102 is connected to the terminal 104 through a network. The above-mentioned network includes but not limited to: a wide area network, a metropolitan area network or a local area network. The terminal 104 is not limited to a PC, a mobile phone, a tablet computer, and the like. The voice data processing method in this embodiment of the present invention may be executed by the server 102, may also be executed by the terminal 104, and may also be executed jointly by the server 102 and the terminal 104. Wherein, the execution of the voice data processing method in the embodiment of the present invention by the terminal 104 m...

Embodiment 2

[0103] According to an embodiment of the present invention, a voice data processing device for implementing the above voice data processing method is also provided. Figure 6 is a schematic diagram of an optional voice data processing device according to an embodiment of the present invention, such as Figure 6 As shown, the device may include:

[0104] Obtaining module 62, is used for obtaining the I-Vector vector of each speech sample in a plurality of speech samples, and determines the target seed sample in a plurality of speech samples; Calculation module 64, is used for calculating the I-Vector vector of target seed sample respectively The cosine distance between the I-Vector vector of the remaining speech samples of the target, wherein the remaining speech samples of the target are speech samples other than the target seed sample in a plurality of speech samples; and the filtering module 66 is used to at least follow the cosine distance from A target voice sample is obt...

Embodiment 3

[0121] According to an embodiment of the present invention, a server or terminal for implementing the above voice data processing method is also provided.

[0122] Figure 13 is a structural block diagram of a terminal according to an embodiment of the present invention, such as Figure 13 As shown, the terminal may include: one or more (only one is shown in the figure) processor 201, memory 203, and transmission device 205 (such as the sending device in the above-mentioned embodiment), such as Figure 13 As shown, the terminal may also include an input and output device 207 .

[0123] Wherein, the memory 203 can be used to store software programs and modules, such as program instructions / modules corresponding to the voice data processing method and device in the embodiment of the present invention, and the processor 201 executes the software program and modules stored in the memory 203 by running the Various functional applications and data processing, that is, to realize t...

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 discloses a voice data processing method and a voice data processing device. The voice data processing method comprises the following steps: acquiring the I-Vector of each of a plurality of voice samples, and determining a target seed sample in the plurality of voice samples; respectively calculating the cosine distances between the I-Vector of the target seed sample and the I-Vectors of the target residual voice samples, wherein the target residual voice samples are the voice samples besides the target seed sample in the plurality of voice samples; and at least filtering from the plurality of voice samples or the target residual voice samples according to the cosine distances to obtain a target voice sample, wherein the cosine distance between the I-Vector of the target voice sample and the I-Vector of the target seed sample is higher than a first preset threshold value. With the adoption of the method and the device, the technical problem that in the relevant technologies, cleansing can not be carried out on voice data by adopting a manual annotation method, so that the voice data cleansing efficiency is low is solved.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a voice data processing method and device. Background technique [0002] In various fields of artificial intelligence, data is crucial, and in many cases the quality of data plays a decisive role. However, the quality of data in the actual situation is mostly uneven, and it needs to be processed further. Data processing generally refers to removing the "noise" in the data and retaining the real data needed. In the field of voiceprint recognition, the voiceprint samples of a specific person obtained through the Internet are in most cases impure. In addition to noise such as non-human voices, they may also contain the voices of other people. How to clean out the noise and other human voices, and only keep the voiceprint voice samples of this specific person is the main problem we are facing today. [0003] At present, in order to obtain voice samples of a specific person's voicepr...

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): G10L17/08G10L21/0272
CPCG10L17/08G10L21/0272G10L17/20G10L17/04G10L25/21
Inventor 金星明李为郑昉劢吴富章朱碧磊钱柄桦李科吴永坚黄飞跃
Owner TENCENT TECH (SHENZHEN) CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap