A Speech Signal Similarity Detection Method
A voice signal and detection method technology, applied in voice analysis, instruments, etc., can solve the problems of low reference significance and low accuracy of the channel to be tested, and achieve the goal of facilitating popularization and application, improving accuracy, and reducing occasional noise interference. Effect
Active Publication Date: 2019-10-18
成都普创通信技术股份有限公司
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
When the existing method is used to detect the similarity of speech segments, the accuracy of the detection is low due to the influence of occasional noise interference, and the reference value is not significant when measuring the performance of the channel to be tested.
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
Embodiment
[0042] like figure 1 Shown, a kind of voice signal similarity detection method comprises the following steps: step 1, the reference voice signal in the reference channel and the voice signal to be tested in the channel to be tested are all extracted to obtain N sections of voice fragments, and the N sections of reference voice signals The speech fragments of the speech segments and the N sections of the speech signals to be tested are sorted respectively, and the speech fragments of the N sections of the reference speech signals are corresponding to the speech fragments of the N sections of the speech signals to be tested; wherein, N is an integer not less than 2; Step 2, calculate the similarity of each segment of the speech segment of the speech signal to be tested and the speech segment of the corresponding reference speech signal thereof one by one; Step 3, the speech segment of the N segment of the speech signal to be tested and the speech of the corresponding reference sp...
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 discloses a voice signal similarity detection method, comprising the following steps: step 1, extracting reference voice signals in a reference channel and voice signals to be detected in a channel to be detected to obtain N voice fragments, sequencing the voice fragments of the N fragments of reference voice signals and the voice fragments of the N fragments of voice signals to be detected respectively, and allowing the voice fragments of the N fragments of reference voice signals to correspond to the voice fragments of the N fragments of voice signals to be detected one by one; step 2, gradually calculating the similarity between the voice fragment of each fragment of voice signals to be detected and the voice fragment of the corresponding fragment of reference voice signals; and step 3, after the similarities between the voice fragments of the N fragments of voice signals to be detected and the voice fragments of the corresponding reference voice signals are calculated, calculating a cumulative similarity mean by adopting a cumulative mean calculation method. The method can improve the accuracy of detecting the voice similarity between the channel to be detected and the reference channel, and thus can be popularized and applied on the aspect of measuring the performance of the channel to be detected.
Description
technical field [0001] The invention relates to the technical field of audio processing, in particular to a method for detecting similarity of speech signals. Background technique [0002] Audio is an important medium for multimedia applications. The frequency range of audio signals that people can hear is about 20Hz-20kHz, and the voice signals are about 300Hz-4kHz. The detection of the performance of the signal transmission channel is often involved in the transmission of audio signals. At present, people generally test the performance of the channel to be tested by detecting the similarity of speech segments between the channel to be tested and the reference channel. When the existing method is used to detect the similarity of speech segments, the accuracy of the detection is low due to the influence of occasional noise interference, and the reference value is not significant when measuring the performance of the channel to be tested. Contents of the invention [0003]...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G10L25/51G10L21/0208
Inventor 张洪英张杰良成立然郑泽俊
Owner 成都普创通信技术股份有限公司