Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Phoneme marking method and device based on audio fingerprint

A technology of audio fingerprinting and marking method, which is applied in speech analysis, instruments, etc., can solve the problems of low efficiency, time-consuming, and manpower, and achieve the effect of avoiding the influence of noise and reducing the comparison time

Inactive Publication Date: 2019-05-28
SPEAKIN TECH CO LTD
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the method of manual identification or pure machine extraction is mainly used. The manual identification method has high accuracy, but it requires a lot of manpower, takes a long time and is inefficient.

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
  • Phoneme marking method and device based on audio fingerprint
  • Phoneme marking method and device based on audio fingerprint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] This embodiment provides a phoneme marking method based on audio fingerprints, which is applicable to phoneme marking application scenarios in the field of speech recognition, and can improve marking efficiency. The phoneme marking method based on audio fingerprints consists of a phoneme marking device based on audio fingerprints implemented by software and / or hardware.

[0037] figure 1 It is a flow chart of the audio fingerprint-based phoneme marking method provided in Embodiment 1.

[0038] see figure 1 , the phoneme marking method based on audio fingerprints comprises the steps:

[0039] S10. Perform pre-emphasis, framing and preprocessing of adding a Hamming window to the speech signal to obtain the speech to be marked.

[0040] Specifically, the purpose of the pre-emphasis of the speech signal is to emphasize the high-frequency part of the speech, remove the influence of lip radiation, and increase the high-frequency resolution of the speech. After the pre-emp...

Embodiment 2

[0048] The audio fingerprint-based phoneme marking device provided in this embodiment can be used to implement the audio fingerprint-based phoneme marking method provided in the embodiment of the present invention, and has corresponding functions and beneficial effects.

[0049] figure 2 A structural block diagram of an audio fingerprint-based phoneme marking device provided in Embodiment 2.

[0050] see figure 2 , a phoneme marking device based on audio fingerprints, comprising:

[0051] Preprocessing unit 1 is used to carry out pre-emphasis, framing and preprocessing of adding Hamming window to the speech signal to obtain the speech to be marked;

[0052] The pole acquisition unit 2 is used to extract the audio fingerprint of the voice to be marked, and obtains the voice spectrum pole information of the audio fingerprint of the voice to be marked; the extreme point acquisition unit 2 is specifically used to extract the audio fingerprint of the voice to be marked, and obt...

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 technical field of vocal print identification, and in particular discloses a phoneme marking method and device based on audio fingerprint. The method comprises the following steps: extracting audio fingerprint of a to-be-marked voice, and acquiring voice frequency spectrum pole point information of the audio fingerprint of the to-be-marked voice; comparing the pole point information with all audio fingerprint in a phoneme database so as to obtain N retrieval phonemes with the highest matching values, wherein N is a natural number; judging whether former N retrievalphonemes have one retrieval phoneme of which the pronunciation is identical to that of a phoneme to be marked or not; if so, confirming the N retrieval phonemes as marking phonemes of the to-be-marked voice. The invention provides the phoneme marking method and device based on audio fingerprint, only frequency spectrum pole points are selected for comparison, thus the comparison time can be shortened, and an effect of rapid marking is achieved.

Description

technical field [0001] The invention relates to the technical field of voiceprint identification, in particular to a phoneme marking method based on audio fingerprints. Background technique [0002] Audio fingerprint technology is accomplished by extracting the data features in the sound and comparing the content to be identified with the established audio fingerprint database. The recognition process is not affected by the storage format, encoding method, bit rate and compression technology of the audio itself. The matching of audio fingerprints is a highly accurate match, which does not depend on the elements of the file to provide meta-information of the relevant page, watermarking and file hash value. [0003] A phoneme is the smallest unit in speech. It is analyzed according to the pronunciation actions in a syllable, and an action constitutes a phoneme. Phonemes are divided into two categories: vowels and consonants. [0004] Voiceprint identification, also known as...

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): G10L17/02G10L25/18G10L25/54
Inventor 郑棉洲潘雷明陈昊亮
Owner SPEAKIN TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products