Voice data searching method and system

A voice data and search method technology, applied in voice analysis, instruments, etc., can solve problems such as difficulty in voice data search, and achieve the effect of enhancing user experience

Active Publication Date: 2016-10-12
NUBIA TECHNOLOGY CO LTD
View PDF12 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to propose a voice data se...

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 searching method and system
  • Voice data searching method and system
  • Voice data searching method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Such as image 3 As shown, the first embodiment of the present invention proposes a voice data search method, the method includes the following steps:

[0066] S100. Receive a search instruction input by a user.

[0067] Specifically, a search key is provided in the mobile terminal, and when the user needs to search for voice data, the user operates the search key (for example, touches or presses it) to issue a search command and activate the function of searching voice data. In this embodiment, the search key may be a physical home key or a virtual home key.

[0068] S200. Receive voice information input by a user.

[0069] Specifically, after receiving the user's search instruction, the display interface of the mobile terminal prompts the user to input voice information. In this embodiment, the user continuously touches or presses the search key to input voice information, and can choose to input through earphones or a microphone configured on the mobile terminal. ...

Embodiment 2

[0082] Such as Figure 4 As shown, the second embodiment of the present invention proposes a voice data search method. In the second embodiment, the voice data search method is similar to the steps in the first embodiment, the difference is that it also includes steps before step S100:

[0083] S102. Establish a keyword database corresponding to the voice data.

[0084] Specifically, the voice data in the mobile terminal is converted into text information through voice recognition technology, and stored in the keyword database uniformly, and each piece of text information is associated with the corresponding voice data.

[0085] In this embodiment, step S500 specifically includes searching the keyword database corresponding to the voice data to be matched according to the confirmed search condition, so as to find the voice data matching the search condition.

[0086] The voice data search method proposed in this embodiment converts the voice data in the mobile terminal into ...

Embodiment 3

[0088] Such as Figure 5 As shown, the third embodiment of the present invention proposes a voice data search method. In the third embodiment, the voice data search method is similar to the steps of the second embodiment, the difference is that step S102 is replaced by step S104, and steps S300 and S400 are replaced by step S304. The method specifically includes the following steps:

[0089] S104, establishing a voiceprint database corresponding to the voice data.

[0090] Specifically, the speech data in the mobile terminal is subjected to voiceprint feature extraction to generate voiceprint information, which is uniformly stored in the voiceprint database, and each piece of voiceprint information is associated with the corresponding voice data. The voiceprint feature extraction includes using the cepstrum method to calculate the pitch period parameters, and then converting the voice signal power into Mel cepstral coefficients (MFCC) through the Mel filter, and using the fe...

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 searching method and system, belonging to the data retrieval field. The method comprises: receiving a search instruction, voice information and a fuzzy searching scope inputted by a user through operating a search key; determining search conditions according to received voice information and fuzzy search scope, the search conditions being the number of characters separated between a keyword determined by the voice information inputted by the user and a keyword determined by the fuzzy searching scope, and/or the voiceprint recognition (VPR) characteristics of the voice information; and searching for voice data according to determined search conditions, and finding voice data matching the search conditions. Accordingly, the method can rapidly position voice data to be searched by users, and enhance user experience, and is fast and convenient.

Description

technical field [0001] The invention relates to the field of data retrieval, in particular to a voice data search method and system. Background technique [0002] Voiceprint recognition (Voiceprint Recognition, VPR) is a technology that automatically identifies the speaker's identity based on the speech parameters reflecting the speaker's physiological and behavioral characteristics in the speech waveform. It mainly includes two parts: feature extraction and pattern matching. Since the research and development of this technology, it has received special attention for its unique advantages of convenience, economy, safety and accuracy. As a kind of biometric identification technology, this technology is widely used in Internet and communication fields such as voice dialing, telephone banking, telephone shopping, database access, information service, security control, etc. [0003] Speech recognition technology is a technology that allows machines to convert voice signals into...

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): G10L25/54
CPCG10L25/54
Inventor 徐桃
Owner NUBIA TECHNOLOGY 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