Method and system for graded measurement of voice
A measurement method, a technology of speech, used in speech analysis, speech recognition, instruments, etc.
Active Publication Date: 2011-07-20
创而新(北京)教育科技有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in language learning, it is costly to collect a large number of standard pronunciations of speech experts, that is, it is difficult to collect a large amount of training data.
[0005]In a word, due to the difference between speech recognition and speech measurement goals in language learning, the logarithmic likelihood method based on HMM model has high complexity of speech classification judgment and accurate speech classification measurement Defects such as low degree
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 Construction
[0029] figure 1 It is a flow chart of the first embodiment of the method for measuring speech ratings of the present invention. Such as figure 1 As shown, the voice rating determination method includes:
[0030] Step 11, receiving a voice signal.
[0031] The speech signal may at least include a training sample speech signal or a test speech signal. When the voice signal is a training sample voice signal, the corresponding process is a systematic learning and training process; when the voice signal is a test voice signal, the corresponding process is a systematic grading measurement process.
[0032] Step 12. Perform speech recognition on the received speech signal, and obtain a state-aligned speech feature sequence according to the reference text and the reference model.
[0033] The reference text and reference model are stored in the memory bank of the speech classification measurement system. When the speech signal is received, the received speech signal is time-alig...
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 method and a system for graded measurement of voice. The method comprises the following steps: carrying out voice recognition for a received voice signal, and acquiring a voice feature sequence of state alignment according to a reference text and a reference model; correcting a distribution parameter of the reference model according to the voice feature sequence of statealignment, and generating a voice template vector based on the reference model for the voice signal; using a support vector machine classification decision tree to carry out classification decision for the voice template vector, and then, obtaining the classification grade mapped by the voice template vector. A support vector machine is provided by the invention to build a model for a language classification boundary, and the model is applied to language learning with the following steps: fetching the voice feature of the received voice signal, and carrying out state alignment between the received voice signal and the reference model; correcting the distribution parameter of the reference model and generating a corresponding voice template vector; and using the support vector machine classification decision tree to decide the voice template vector, thus, the complexity of the classification decision of voice is effectively reduced, and the accuracy of the graded measurement of voice is improved.
Description
technical field [0001] The invention relates to the field of speech recognition, in particular to a speech classification measurement method and system. Background technique [0002] The essence of speech recognition is to classify speech signals. The focus of traditional speech recognition modeling is to capture the commonality between the pronunciation of the same content by different speakers in different situations. At present, relatively mature speech recognition modeling is based on a hidden Markov model (Hidden MarkovModel, hereinafter referred to as HMM) based on state probability distribution density. In speech recognition based on the HMM model, the commonly used method for calculating the confidence is the log likelihood method (Log Likelihood Ratio, referred to as LLR). LLR = log ( x / Λ ) - log ( x / ...
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): G10L15/00G10L15/08G10L15/14G10L15/02G10L15/06G10L17/16
Inventor 许军张化云陈炜李慧勤
Owner 创而新(北京)教育科技有限公司