Compensation method for different speech coding influence in speaker recognition
A technology of speaker recognition and speech coding, which is applied in the field of speaker recognition, can solve problems such as speaker recognition performance degradation, achieve the effects of reducing recognition rate reduction, reducing voice feature distortion, and increasing average recognition rate
Inactive Publication Date: 2008-12-03
HARBIN INST OF TECH
View PDF0 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The present invention provides a compensation method for the influence of different speech codes in speaker recognition in order to solve the problem of speaker recognition performance decline caused by the mismatch between training speech and test speech codes in the speaker recognition process
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0011] Specific implementation mode one: see figure 1 with figure 2 , this embodiment consists of the following steps:
[0012] Step 1: Use one of uncoded, mp3 coded, rm coded or wma coded codes as the standard coded code, and sequentially perform feature processing and maximum expectation algorithm training on the voice signals of N speakers under the standard coded code to obtain N Speaker Gaussian mixture model {λ n} n＝1 N As a matching object library, where N represents a natural number;
[0013] Step 2, input the voice signal s(n) of the speaker to be identified, and perform feature extraction on the input voice signal to obtain the feature vector sequence X={x 1 , x 2 ,...,x S}, where S represents a natural number;
[0014] Step 3: Select the previous T frames in the feature vector sequence X to obtain the sequence X T ={x 1 , x 2 ,...,x T}, with this T frame sequence X T Perform MAP algorithm adaptively to obtain the deviation h between the current encodin...
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
Login to View More Abstract
The invention relates to a compensating method of different speech coding influence in speaker recognition, in particular to a compensating method for mismatching of the speech coding in the speaker recognition in the Internet so as to solves the problem of degradation of performance of the speaker recognition caused by the mismatching of training speech and test speech coding in the speaker recognition. The method carries out characteristic processing for a voice signal of the speaker under a standard encoding mode and takes a speaker model under the standard encoding mode obtained by expectation-maximization algorithm training as a match object library; the voice signal of the speaker to be recognized is input and treated with characteristic extraction to obtain a characteristic vector sequence; the front T frames in the characteristic sequence are selected to obtain a sequence and then an MAP algorithm is carried out so as to obtain deviation of a current code and a standard code in a self-adapting way; the original characteristic sequence is adjusted and compensated by using the obtained deviation of the current code and the standard code to obtain a new characteristic vector sequence; the new characteristic vector sequence is used for respectively being matched with the speaker model under the standard encoding mode and judging to obtain a recognition result.
Description
technical field [0001] The invention relates to a compensation method in the technical field of speaker recognition, in particular to a compensation method for speech code mismatch in speaker recognition on the Internet. Background technique [0002] Speaker recognition refers to automatically confirming whether the speaker is in the recorded set of speakers through the analysis and processing of the speaker's voice signal, and further confirming who the speaker is. Although in the clean speech environment of the laboratory, the speaker recognition system has achieved relatively good results, but in practical applications, the performance of the speaker recognition system is restricted by many factors, and the recognition results of the system are still unsatisfactory. One of the main reasons affecting the performance is the mismatch of speech signal encoding during training and testing due to various factors. With the development of modern network technology, there are mor...
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
Login to View More IPC IPC(8): G10L17/00G10L17/04
Inventor 韩纪庆李雪林
Owner HARBIN INST OF TECH