A method for identifying speech keywords in broadcast signals
A technology for broadcasting signals and keywords, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of recognition, unrecognized keywords, irrelevant vocabulary errors, etc. The effect of the identified function
Active Publication Date: 2021-06-11
SICHUAN UNIV +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to solve the problems in the prior art that keywords cannot be recognized and many irrelevant words are wrongly "recognized" when automatic speech recognition technology is used to detect illegal broadcasts; a method for recognizing broadcast signals is provided In the voice keyword method, the acoustic model and the text phoneme mapping table are trained by using the recorded samples of keywords. At the same time, since we do not need complete and meaningful sentences, we only need to recognize specific keywords in the voice To determine whether its nature is a normal broadcast or an illegal broadcast, which improves efficiency and simplifies the identification 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
Embodiment
[0050] Such as figure 1 As shown, a method for recognizing voice keywords in a broadcast signal comprises the following steps:
[0051] Step 1, set up the acoustic model; The acoustic model in the present embodiment is a CMU sphinx model; The CMU sphinx model is a hidden Markov-Gaussian mixture model;
[0052] The joint expression formula of the Gaussian mixture model is as follows:
[0053]
[0054] Where x represents a syllable; p(x) is the probability of outputting the syllable; P(m) is the weight of the corresponding Gaussian probability density function; μ m and σ m 2 is the parameter of the corresponding Gaussian distribution; m is the index of the sub-model, that is, the mth sub-model; M is the total number of sub-models; N( ) is the multivariate Gaussian distribution; I is the identity matrix of the corresponding data dimension; P(x |m) is the probability of outputting the syllable for the mth model. In addition, the complete acoustic model is designed based on...
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 method for identifying speech keywords in broadcast signals, comprising the following steps: 1. Establishing an acoustic model; 2. Establishing a text-phoneme mapping table of keywords; 3. Establishing a keyword sequence dictionary; 4. Using the dictionary The keywords in the acoustic model are trained to obtain the mapping between the phonetic characteristics of the keyword and the phonemes, and the mapping is loaded into the acoustic model; 5. Define the mapping between the phonemes and the specified keywords, and the The mapping is saved to the text-phoneme mapping table; 6. Load the trained acoustic model, text-phoneme mapping table and keyword sequence dictionary into the decoder; 7. Denoise the broadcast signal to be recognized and perform feature extraction, and then Load the decoder to get the keyword recognition result. The acoustic model and the text phoneme mapping table are trained by using the samples recorded by keywords. Since we do not need complete meaningful sentences, the error tolerance rate of the text phoneme mapping table is improved.
Description
technical field [0001] The invention relates to the technical field of speech recognition, in particular to a method for recognizing speech keywords in broadcast signals. Background technique [0002] With the continuous development of social economy and radio communication, the importance of radio spectrum resources has become increasingly prominent. Driven by economic interests, many illegal broadcasters purchase and set up broadcast base stations privately, broadcast false advertisements or engage in economic fraud, disrupt economic order, interfere with normal communication signals, and even cause safety accidents. Therefore, it is of great social and economic value to design effective methods for efficient automatic identification and control of illegal broadcast signals. The traditional method of identifying illegal broadcasts mostly adopts the method of manual listening and identification, which has high labor costs and is prone to mistakes. Although automatic speec...
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): G10L15/06G10L15/08G10L15/22
CPCG10L15/063G10L15/08G10L15/22G10L2015/0631
Inventor 雒瑞森孙超武瑞娟杜淼余艳梅龚晓峰
Owner SICHUAN UNIV