Music Recognition Algorithm based on T-S Cognitive Neural Network

Abstract The main task of music recognition is to acquire relevant information of music content through processing and feature extraction of audio signals, and then used for comparison, classification, and automatic recording. The cognitive neural network based on T-S model is used to train the network weights with improved genetic algorithm in the paper. The strategy of membership function parameter adjustment is combined with the combination of momentum method and learning rate adaptive adjustment. The new proposed algorithm can be used in the music recognition algorithm by adding a compensation factor related to the input dimension on the membership degree, and the experimental result of the rule disaster caused by the excessive input dimension shows that the new proposed method can be applied to the music recognition system. At the same time, it shows that the accuracy rate of the recognition network is more accurate than that of the other algorithms, and its robustness is better.


Introduction
Automatic recognition of music is a new interdisciplinary subject, and it relates to the integration concept of multiple disciplines [1]. The main task of music recognition is to acquire relevant information of music content through processing and feature extraction of audio signals, and then used for comparison, classification, and automatic recording. In this paper, the computer recognition of music is the combination of computer multimedia technology, the related knowledge and technology of signal processing and pattern recognition with the music theory [2]. It simulates the process of music cognition analysis by computer, analyzes and analyzes the performance of music and evaluates the performance of the music.
The study of music recognition began in 1970s. The first identification system appeared in 1975. The system in 1996 has been able to deal with more complex piano works. The music recognition network is usually composed of three parts: preprocessing feature extraction and training recognition network. In the study of artificial neural network (ANN) as recognition network, a lot of progress has been made, but the network connection weight value of ANN is the unknown. It is a typical model of black box learning for internal input and output.
The understanding of knowledge stored in the process is a difficult problem, and the weight value is not specific. The fuzzy system is based on the fuzzy set theory created by Zadeh. Its obvious characteristic is that it can express the logic directly and it is conformed to human expression of transcendental knowledge. It has good logical function, but the generation and adjustment of membership functions and rules is the most difficult problem. The FNN algorithm synthesized by the neural network and the fuzzy set concept. It can not only imitate the logical idea of the human brain, but also have the capability of the ANN to handle the quantitative and qualitative knowledge synchronously [3,4]. At present, the most commonly used fuzzy neural network model is Takagi-Sugeno (T-S) model [5].
Cognitive style is the personal preference of people in the way of information processing.
It is the individual difference in the use of brain-based neural structure and mechanism for information processing. It is also the most extensive and profound individual difference in people's cognition, which is considered as a The main task of music recognition is to use music's audio signal to get music content, that is to say, get music score. Simply speaking, it is a conversion system from file wav to file. This system has a wide application prospect in the fields of computer music, computer aided composing and music works digitalization, because it can easily realize the MIDI computer entry work of music score. In order to meet the needs of practical applications, music recognition is committed to the recognition of complex music, which contains multiple voices and involves a large number of harmonies.
Symphony is a typical representative of this type of Polyphonic Music Recognition type music. Monosyllabic recognition involves only one voice and produces only one note at a time, so its recognition object includes only one note. Moreover, because no harmony is involved, the corresponding note can be easily obtained from the pitch frequency of the signal.
The whole recognition task involves only one key technology of pitch frequency extraction. However, because the task of recognition is to get music score, at least two parameters of pitch and pitch of the note should be identified.
The music recognition flowchart is shown as  if there is a m a n input output, the traditional neural network to each output with each input matrix multiplication, the time complexity, and extraction only meaningful k convolutional neural network input, its time complexity is, because in actual application, general is far less than m, k is more practical significance, and this reduces the time complexity, on the one hand and improve the efficiency of storage.

CNN structure based on T-S algorithm
The CNN algorithm is a decision behavior that uses fuzzy reasoning to imitate human being in the uncertain environment [6]. The If the output vector is Y, the fuzzy rules of the proposed methods is in the form of (1) According to the fuzzy model given above, system diagram of the proposed algorithm is shown in Figure 2. The network is composed of two parts of the forward part network and the post part network. The forward part network is satisfied with the fuzzy rules, and the post part is related to produce the post of the fuzzy rules.
We will analyze each layer of the network, and give the node functions of each layer: Input layer: Each node is directly connected to each node i x , and it plays the role of sending the input information to the next level.
i i The input value of the zero nodes in the input layer is The middle 1-layer of forward part network: Each node represents the value of one language variables. Its effect is to compute membership functions of all input components in fuzzy sets of linguistic variables.    Each node represents a rule whose action is to express the consequent of formulating rule.

Simulation experiment 2
The recognition process is based on the various states that are estimated by the feature flow, As is shown in the Table 2 and Figure 4, the training set is the 61 note played for the piano. It can be seen from this table that the recognition rate is insensitive to both within and outside. The recognition error of piano music is mentioned in the above experimental results; therefore, by adjusting the parameters, the system performance can be further improved. Compared with the recognition rate mentioned above, the performance of the system has been greatly improved. This shows that T-S fuzzy neural network is effective in music recognition.

Conclusions
The fuzzy neural network based on T-S model is to the music recognition system. At the same time, it shows that the accuracy rate of the recognition network is more accurate than that of the other algorithms, and its robustness is better.