Music Information Research Articles

Musical Tones Classification using Machine Learning

Abstract: In today's scenario, most things are digitized. Music is one of the most famous forms of art, learned by different people and taught by several musicians. Therefore, music information retrieval (MIR) and its applications are gaining popularity following advances in machine learning technology. Various applications such as genre recognition, song recognition, automatic score generation, music transcription, tempo, beat type, etc. have been developed to achieve this goal. However, little research has been done to identify musical instruments. The new method proposed here develops a machine learning model in combination with the Mel-frequency-cepstral-coefficient by extracting audio features directly from the raw audio dataset. A total of 600 audio files containing sound samples from 6 different instruments are used for system training and instrument prediction.

Historical Stages of Musical Art Development in the Context of Scientific and Technical Progress

The purpose of the work is to define the historical milestones of scientific and technological progress and to identify the interrelationship of art, technique, and technology at various stages of world culture development. The research methodology is based on philosophical and aesthetic research on the evolution of artistic culture and the understanding of the musical-communicative process, which allows the summing up and substantiating of the conclusions of the outlined issues. The scientific novelty of the work consists in gradually highlighting the historical stages of the scientific and technical revolution, demonstrating its direct influence on the development of musical art from the first stages of its development to the present day. It has been determined that in each historical formation, transformational processes are closely related to scientific and technical progress, which today are the main driving force of the musical and technical industry. Conclusions. The first stage is marked by the emergence of writing, which destroyed the monopoly of a small number of people on knowledge. At this stage, musical notation appears, with the help of which the information related to music is broadcasted. In the second stage, the invention of the printing press becomes a means of rapid dissemination of information, including musical information, through sheet music printing. The third stage is associated with the invention of mechanical sound recording and sound reproduction devices, as well as the introduction of electric current and analogue sound recording devices. In the fourth stage, because of modern technological achievements, the so-called phenomenon of "digital arts" is formed, which is characterised by interactivity, elitism, a new genre system, and innovative means of artistic expression. Modern artistic technologies, relying on the latest sound processors, computer software, and other digital innovations, help to expand the boundaries and create a new sound palette in music and concert practice, theatre performances, studio work, radio broadcasting, screen arts, and other areas of cultural and artistic life. Key words: musical art, scientific and technical progress, information revolutions, computer technologies, digital arts

An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking

In music information retrieval (MIR), beat tracking is one of the most fundamental tasks. To obtain this critical component from rhythmic music signals, a previous beat tracking system of hidden Markov model (HMM) with a recurrent neural network (RNN) observer was developed. Although the frequency of music beat is quite stable, existing HMM based methods do not take this feature into account. Accordingly, most of hidden states in these HMM-based methods are redundant, which is a disadvantage for time efficiency. In this paper, we proposed an efficient HMM using hidden states by exploiting the frequency contents of the neural network’s observation with Fourier transform, which extremely reduces the computational complexity. Observers that previous works used, such as bi-directional recurrent neural network (Bi-RNN) and temporal convolutional network (TCN), cannot perceive the frequency of music beat. To obtain more reliable frequencies from music, a periodic recurrent neural network (PRNN) based on attention mechanism is proposed as well, which is used as the observer in HMM. Experimental results on open source music datasets, such as GTZAN, Hainsworth, SMC, and Ballroom, show that our efficient HMM with PRNN is competitive to the state-of-the-art methods and has lower computational cost.

The effect of the structured introduction as a cognitive strategy in the collection and retention of musical information among the students of the Art Education Branch - Teachers Colleg

من الحقائق المسلم بها أن هدف التدريس هو تحقيق المرغوب فيه في سلوك المتعلم وأداته في ذلك عوامل ومتغيرات شتى يقف على رأسها المعلم واستراتيجيته في تحقيق التغيير في ذلك السلوك عبر الجهد الكبير في زيادة قدرة المتعلم العقلية في خزن المعلومات واسترجاعها واإلفادة منها كلما اقتضت الحاجة.

VAT-SNet: A Convolutional Music-Separation Network Based on Vocal and Accompaniment Time-Domain Features

The study of separating the vocal from the accompaniment in single-channel music is foundational and critical in the field of music information retrieval (MIR). Mainstream music-separation methods are usually based on the frequency-domain characteristics of music signals, and the phase information of the music is lost during time–frequency decomposition. In recent years, deep learning models based on speech time-domain signals, such as Conv-TasNet, have shown great potential. However, for the vocal and accompaniment separation problem, there is no suitable time-domain music-separation model. Since the vocal and the accompaniment in music have a higher synergy and similarity than the voices of two speakers in speech, separating the vocal and accompaniment using a speech-separation model is not ideal. Based on this, we propose VAT-SNet; this optimizes the network structure of Conv-TasNet, which sets sample-level convolution in the encoder and decoder to preserve deep acoustic features, and takes vocal embedding and accompaniment embedding generated by the auxiliary network as references to improve the purity of the separation of the vocal and accompaniment. The results from public music datasets show that the quality of the vocal and accompaniment separated by VAT-SNet is improved in GSNR, GSIR, and GSAR compared with Conv-TasNet and mainstream separation methods, such as U-Net, SH-4stack, etc.

A neural harmonic-aware network with gated attentive fusion for singing melody extraction

Singing melody extraction from polyphonic musical audio is one of the most challenging tasks in music information retrieval (MIR). Recently, data-driven methods based on convolutional neural networks (CNNs) have achieved great success for this task. In the literature, harmonic relationship has been proven crucial for this task. However, few existing CNN-based singing melody extraction methods consider the harmonic relationship in the training stage. The state-of-the-art CNN based methods are not capable of capturing such long-dependency harmonic relationship due to limited receptive field and unacceptable computation cost. In this paper, we introduce a neural harmonic-aware network with gated attentive fusion (NHAN-GAF) for singing melody extraction. Specifically, in the 2-D spectrograms modeling branch, we propose to employ multiple parallel 1-D CNN kernels to capture the harmonic relations between 1–2 octaves along the frequency axis in the spectrogram. Considering the advantage of jointly using Time–Frequency (T-F) domain and time domain information, we use two-branch neural nets to learn discriminative representation for this task. A novel gated attentive fusion (GAF) network is suggested to encode potential correlations between the two branches and fuse the descriptors learned from raw waveform and T-F spectrograms. Moreover, the idea of GAF can be exploited to the multimedia applications with multimodal analysis. With the two proposed components, our proposed model is capable of learning the harmonic relationship in the spectrogram and better capturing the contextual but discriminative features for singing melody extraction. We use part of the vocal tracks of the RWC dataset and MIR-1 K dataset to train the model and evaluate the performance of the proposed model on the ADC 2004, MIREX 05 and MedleyDB datasets. The experimental results show that the proposed method outperforms the state-of-the-art ones.

AN INVESTIGATION OF THE EMOTIONAL DIMENSION IN SONGS SUNG BY NEŞET ERTAŞ: AN APPLICATION OF EMOTIONAL INDEX

This article aims to highlight the emotional characteristics of the lyrics and compositions of the folk songs sung by Neşet Ertaş. For this purpose, the lyrics of 339 songs and the musical information of 264 compositions were crawled. There is also a speech among them. Three different sources have been used to obtain the lyrics and text of speech. Besides, an additional process on to them has been applied; finally, verse-based or sentence-based texts have been obtained. In this process, these texts have been removed from certain words that do not have a meaning on their own, such as unnecessary punctuations, stopwords, onomatopoeic words, question suffixes, and transformed into a plain form. After this stage, verses or sentences have been made processable. First of all, to find the Turkish sentiments of each lyric, state-of-the-art machine learning techniques have been applied to them, and the sentiment scores of each lyric have been computed. Three different machine learning models have been used to calculate sentiment scores. These three different models are re-trained for the Turkish sentiments, which are of the models developed by Google. Only a single sentiment score has been obtained for each verse or sentence. The average of this sentiment score obtained from three different models has been calculated and used to satisfy consistency. Afterward, a sentiment vector consisting of the verse of each song or each sentence of the speech text has been created. The average of this sentiment vector is the overall score of that text (song or speech). The variance of this sentiment vector has also been calculated, in which this variance has been used to measure the sentiment tides in the song or speech text. Later, some valuable variables from a widely used music listening platform have been obtained as a basis for composition information. Here, 10 variables named acousticness, danceability, energy, instrumentalness, liveness, loudness, speechiness, tempo, valence, popularity have been obtained. Three of them, danceability, energy, and valence variables have been taken into account to estimate the emotional score of the composition by getting the average of these three variables. These scores are going to be matched then with the musical information of compositions of each unique song which are 169 intersectional sets of them, and an emotional map has been drawn statistically, which can be modeled with the dimension of sentiments of lyrics and sentiments of composition showing Neşet Ertaş's emotional map. In the map of emotions, the axes have been set in the range of (-1, +1). Therefore, the scores obtained for both texts and compositions have been rescaled in the range of (-1, +1) with a formula generated for this purpose, which makes the scores of both texts and compositions are made comparable. After this stage, the sentiments of the texts are placed on the x-axis for the map of emotions while composition sentiments are placed on the y-axis. On the x-axis, which is called the lyrics scale, a score of -1 is indicated by feelings of "sorrow", and a score of +1 is indicated by feelings of "happy". The composition scale, on the other hand, shows -1 score as “melancholic” and +1 score as “cheerful” on the y-axis. According to the results obtained, it has been determined that the dominant characteristic of Neşet Ertaş's lyrics is based on sorrow words and that most of his folk songs are grouped in sorrowful lyrics and melancholic compositions. In addition, it has been found that his words are characterized by emotional changes and emotional tides; it has been also determined thanks to word cloud analysis that he often has given humane and moral advice in phrases in the lyrics. Keywords: Neşet Ertaş, Sentiment Analysis, Sentiment Index, Machine Learning, Deep Learning.

The digital archiving of music at the Danish Broadcasting Corporation

In this article I offer a history of the digital music archive at the Danish Broadcasting Corporation (DR). Within the last decade, DR has complemented their music archive with an in-house digital music platform called /Diskoteket,1 on which I see not only a lively and educational space for making contextualized searches in regard to recorded and commercially released music, but also a determinative discourse on music information. As a conceptual point of departure I investigate the supposition that DR has an institutionalized understanding of music history, and building on this supposition I aim to throw light on the following question: how can an institutionalized music history at DR be traced in online music presentations?

Introduction

Introduction

A Postcolonial MIR?

The field of music information retrieval (MIR) offers tools for the analysis of music and sound, for example in archives of historical recordings; but it has also been widely critiqued for bias toward Western music and Western epistemologies. There seems to be a gap, or even an irresolvable friction, between computer science-based MIR tools, problems, and methodologies, on the one hand, and, on the other hand, humanities-based research in music and media that examines sound from critical and postcolonial perspectives. This essay draws from sound studies and critical technology studies to propose that this is an opportune moment for interdisciplinary collaborations between humanities scholars and technologists to enhance critical analyses of music and sound. Key to such collaborations would be a consideration of ontological differences between the two approaches, such as divergent understandings of the fundamental concepts of music, genre, and difference. The essay takes several examples from the author’s research into sound and Dutch colonialism at the Netherlands Institute for Sound and Vision media archive in order to propose some examples of how MIR’s technological tools could potentially enhance critical humanities-driven analyses of sound, perception, and colonial difference. More broadly, the essay argues, the divergences and even tensions between disciplines can be productive for scholarly reflexivity, postcolonial or anticolonial scholarship, and applications of technological tools toward social justice goals.

Polskie kompozytorki baletów. Rekonesans

ABSTRACT Female ballet composers. A Reconnaissance While Polish theoretical and musicological reflection seems to treat ballet music as a poor relation, ballet works composed by women appear as a complete tabula rasa. The present author decided to contribute to filling it by analysing works of Polish female composers of the 20th and 21st centuries. Statistical calculations based on three databases including Polish Music Information Centre (POLMIC), polishstage. pl (e-teatr) and taniecpolska.pl portals as well as own research have revealed 35 Polish female composers of the 20thand 21st centuries have written at least one or more works whose subtitles contain the words “ballet” or “ballet music” or have been composed particularly for a dance theatre, pantomime or dance performance. Out of 122 compositions, twenty ballets have not been staged. The works composed for other types of “dance shows” were written in collaboration with specific choreographers, therefore they have all been staged, except for three compositions. The first Polish female composer to write ballet music was Anna Maria Klechniowska. Her two earliest ballets, Bilitis and Juria were composed in the interwar period, and the third one titled Fantasma in 1964. The most successful female composer was Jadwiga Szajna-Lewandowska who composed ballets for children. Her most popular work was ballet Pinokio [Pinocchio]. Another question refers to stage productions of ballets composed by women. Eighteen of the ballets staged were choreographed by men, and fourteen by women. In the case of music composed strictly for “dance shows” (dance theatre, pantomime or dance performance) female choreographers prevail (47): only twelve male choreographers decided to collaborate with a female composer. Two performances were the result of collaborative work. The findings to date constitute a point of departure for further research into music composed “for dance” (ballet, pantomime, dance theatre and dance performances).

Polskie kompozytorki baletów. Rekonesans

ABSTRACT Female ballet composers. A Reconnaissance While Polish theoretical and musicological reflection seems to treat ballet music as a poor relation, ballet works composed by women appear as a complete tabula rasa. The present author decided to contribute to filling it by analysing works of Polish female composers of the 20th and 21st centuries. Statistical calculations based on three databases including Polish Music Information Centre (POLMIC), polishstage. pl (e-teatr) and taniecpolska.pl portals as well as own research have revealed 35 Polish female composers of the 20thand 21st centuries have written at least one or more works whose subtitles contain the words “ballet” or “ballet music” or have been composed particularly for a dance theatre, pantomime or dance performance. Out of 122 compositions, twenty ballets have not been staged. The works composed for other types of “dance shows” were written in collaboration with specific choreographers, therefore they have all been staged, except for three compositions. The first Polish female composer to write ballet music was Anna Maria Klechniowska. Her two earliest ballets, Bilitis and Juria were composed in the interwar period, and the third one titled Fantasma in 1964. The most successful female composer was Jadwiga Szajna-Lewandowska who composed ballets for children. Her most popular work was ballet Pinokio [Pinocchio]. Another question refers to stage productions of ballets composed by women. Eighteen of the ballets staged were choreographed by men, and fourteen by women. In the case of music composed strictly for “dance shows” (dance theatre, pantomime or dance performance) female choreographers prevail (47): only twelve male choreographers decided to collaborate with a female composer. Two performances were the result of collaborative work. The findings to date constitute a point of departure for further research into music composed “for dance” (ballet, pantomime, dance theatre and dance performances).

Community Based Music Information Retrieval: A Case Study of Digitizing Historical Klezmer Manuscripts from Kyiv

In this article we provide a case study in the datafication of historical handwritten manuscripts, which diversifies the repertoire, approaches, demographics, and institutional partnerships of MIR. The Kiselgof-Makonovetsky Digital Manuscript Project (KMDMP) is a community-based project to digitize music and text, teach, and make music from facsimiles of manuscripts held by the Vernadsky National Library of Ukraine. The corpus comprises 850 high-resolution photographs of handwritten music manuscripts and catalog pages, with a total of around 1,300 melodies. Much of the music was collected by pioneering Belarusian ethnographer Zusman Kiselgof among Jewish communities in the ‘Pale of Settlement’ (mostly in modern Ukraine and Belarus) during the An-Ski Expeditions of 1912–1914. The repertoire is mixed, combining typical Jewish dance and non-dance genres, European society and folklore dance music, and a relatively small quantity of songs and liturgical chant settings. The project simultaneously encodes music in formats accessible to computational musicology and enhances a creative musical community and deeply valued heritage. We introduce the project in dialogue with a recent article by Georgina Born on diversity in the field of MIR; present the material, issues for datafication, and results thus far; describe project elements that enhance musical community; demonstrate the diversity of participants with respect to age, gender, nationality, and profession; outline implications for MIR and computational ethnomusicology; and suggest new funding models and partnerships in support of cultural heritage documentation, preservation, continuity, and analysis.

REAL TIME SPEECH EMOTION RECOGNITION USING MACHINE LEARNING

A speech recognition system, which can detect emotions contained in the dataset such as sad, happy, neural, angry, disgust, surprised, fearful and calm expressions. In real time we can use this application in various decisions. Although we are in a pandemic situation all processes are taking place only through online like job interviews, doctor appointments etc. In these cases this application is very useful whether in what state they are and to detect their emotions through speech. Here we are using a library called Librosa. Librosa is a python package for music and audio analysis. It provides the building blocks necessary to concoct music information retrieval systems. It was developed by Brian McFee, assistant professor of music technology and data science at NYU, and creator of Librosa, a python package for music and audio analysis. Librosa upholds a few elements connected with sound records handling and extraction like burden sound from a circle, register of different spectrogram portrayals, symphonious percussive source detachment, conventional spectrogram decay, stacks and translates the sound, Timespace sound handling, successive demonstrating, coordinating consonant percussive partition, beatsimultaneous and some more.

JSD: A Dataset for Structure Analysis in Jazz Music

Given a music recording, music structure analysis aims at identifying important structural elements and segmenting the recording according to these elements. In jazz music, a performance is often structured by repeating harmonic schemata (known as choruses), which lay the foundation for improvisation by soloists. Within the fields of music information retrieval (MIR) and computational musicology, the Weimar Jazz Database (WJD) has turned out to be an extremely valuable resource for jazz research. Containing high-quality solo transcriptions for 456 solo sections, the dataset opened up new avenues for the understanding of creative processes in jazz improvisation using computational methods. In this paper, we complement this dataset by introducing the Jazz Structure Dataset (JSD), which provides annotations on structure and instrumentation of entire recordings. The JSD comprises 340 recordings with more than 3000 annotated segments, along with a segment-wise encoding of the solo and accompanying instruments. These annotations provide the basis for training, testing, and evaluating models for various important MIR tasks, including structure analysis, solo detection, or instrument recognition. As an example application, we consider the task of structure boundary detection. Based on a traditional novelty-based as well as a more recent data-driven approach using deep learning, we indicate the potential of the JSD while critically reflecting on some evaluation aspects of structure analysis. In this context, we also demonstrate how the JSD annotations and analysis results can be made accessible in a user-friendly way via web-based interfaces for data inspection and visualization. All annotations, experimental results, and code for reproducibility are made publicly available for research purposes.

Induced Emotion-Based Music Recommendation through Reinforcement Learning

Music is widely used for mood and emotion regulation in our daily life. As a result, many research works on music information retrieval and affective human-computer interaction have been proposed to model the relationships between emotion and music. However, most of these works focus on applications in a context-sensitive recommendation that considers the listener’s emotional state, but few results have been obtained in studying systems for inducing future emotional states. This paper proposes Moodify, a novel music recommendation system based on reinforcement learning (RL) capable of inducing emotions in the user to support the interaction process in several usage scenarios (e.g., games, movies, smart spaces). Given a target emotional state, and starting from the assumption that an emotional state is entirely determined by a sequence of recently played music tracks, the proposed RL method is designed to learn how to select the list of music pieces that better “match” the target emotional state. Differently from previous works in the literature, the system is conceived to induce an emotional state starting from a current emotion instead of capturing the current emotion and suggesting certain songs that are thought to be suitable for that mood. We have deployed Moodify as a prototype web application, named MoodifyWeb. Finally, we enrolled 40 people to experiment MoodifyWeb, employing one million music playlists from the Spotify platform. This preliminary evaluation study aimed to analyze MoodifyWeb’s effectiveness and overall user satisfaction. The results showed a highly rated user satisfaction, system responsiveness, and appropriateness of the recommendation (up to 4.30, 4.45, and 4.75 on a 5-point Likert, respectively) and that such recommendations were better than they thought before using MoodifyWeb (6.45 on a 7-point Likert).

Musical expertise shapes visual-melodic memory integration.

Music can act as a mnemonic device that can elicit multiple memories. How musical and non-musical information integrate into complex cross-modal memory representations has however rarely been investigated. Here, we studied the ability of human subjects to associate visual objects with melodies. Musical laypersons and professional musicians performed an associative inference task that tested the ability to form and memorize paired associations between objects and melodies ("direct trials") and to integrate these pairs into more complex representations where melodies are linked with two objects across trials ("indirect trials"). We further investigated whether and how musical expertise modulates these two processes. We analyzed accuracy and reaction times (RTs) of direct and indirect trials in both groups. We reasoned that the musical and cross-modal memory demands of musicianship might modulate performance in the task and might thus reveal mechanisms that underlie the association and integration of visual information with musical information. Although musicians showed a higher overall memory accuracy, non-musicians' accuracy was well above chance level in both trial types, thus indicating a significant ability to associate and integrate musical with visual information even in musically untrained subjects. However, non-musicians showed shorter RTs in indirect compared to direct trials, whereas the reverse pattern was found in musicians. Moreover, accuracy of direct and indirect trials correlated significantly in musicians but not in non-musicians. Consistent with previous accounts of visual associative memory, we interpret these findings as suggestive of at least two complimentary mechanisms that contribute to visual-melodic memory integration. (I) A default mechanism that mainly operates at encoding of complex visual-melodic associations and that works with surprising efficacy even in musically untrained subjects. (II) A retrieval-based mechanism that critically depends on an expert ability to maintain and discriminate visual-melodic associations across extended memory delays. Future studies may investigate how these mechanisms contribute to the everyday experience of music-evoked memories.

Structural Segmentation and Labelling of Tabla Solo Performances

Tabla is a North Indian percussion instrument that serves as both an accompaniment and a captivating solo instrument. Tabla solo is intricate and elaborate, exhibiting rhythmic evolution through a sequence of homogeneous sections marked by shared rhythmic characteristics. Each section has a specific structure and name associated with it. Tabla learning and performance in the Indian subcontinent is based on stylistic schools called gharānās. Several compositions by various composers from different gharānās are played in each section. This paper addresses the task of segmenting the tabla solo concert into musically meaningful sections. We then assign suitable section labels and recognise gharānās from the sections. We have curated a diverse collection of more than 38 hours of solo tabla recordings for the task. We motivate the problem and present different challenges and facets of the tasks. Inspired by the distinct musical properties of tabla solo, we compute several rhythmic and timbral features for the segmentation task. This work explores the approach of automatically locating the significant changes in the rhythmic structure by analysing local self-similarity in an unsupervised manner. We also explore the supervised random forest and a convolutional neural network trained on hand-crafted features. Both supervised and unsupervised approaches are also tested on a set of held-out recordings. Segmentation of an audio piece into its structural components and labelling is crucial to many music information retrieval applications like repetitive structure finding, audio summarisation, and fast music navigation. This work enables a comprehensive musical understanding and description of tabla solo concerts.

Study on Music Emotion Recognition Based on the Machine Learning Model Clustering Algorithm

In recent years, the explosive growth of online music resources makes it difficult to retrieve and manage music information. To efficiently retrieve and classify music information has become a hot research topic. Thayer’s two-dimensional emotion plane is selected as the basis for establishing the music emotion database. Music is divided into five categories, the concept of continuous emotion perception is introduced, and music emotion is regarded as a point on a two-dimensional emotional plane, together with the two sentiment variables to determine its location. The artificial labeling method is used to determine the position range of the five types of emotions on the emotional plane, and the regression method is used to obtain the relationship between the VA value and the music features so that the music emotion classification problem is transformed into a regression problem. A regression-based music emotion classification system is designed and implemented, which mainly includes a training part and a testing part. In the training part, three algorithms, namely, polynomial regression, support vector regression, and k-plane piecewise regression, are used to obtain the regression model. In the test part, the input music data is regressed and predicted to obtain its VA value and then classified, and the system performance is considered by classification accuracy. Results show that the combined method of support vector regression and k-plane piecewise regression improves the accuracy by 3 to 4 percentage points compared to using one algorithm alone; compared with the traditional classification method based on a support vector machine, the accuracy improves by 6 percentage points. Music emotion is classified by algorithms such as support vector machine classification, K-neighborhood classification, fuzzy neural network classification, fuzzy K-neighborhood classification, Bayesian classification, and Fisher linear discrimination, among which the support vector machine, fuzzy K-neighborhood, and the accuracy rate of music emotion classification realized by Fisher linear discriminant algorithm are more than 80%; a new algorithm “mixed classifier” is proposed, and the music emotion recognition rate based on this algorithm reaches 84.9%.

Recognition of Continuous Music Segments Based on the Phase Space Reconstruction Method.

Piano score recognition is one of the important research contents in the field of music information retrieval, and it plays an important role in information processing. In order to reduce the influence of vocals on the progress of piano notes and restore the harmonic information corresponding to piano notes, the article models the harmonic information and vocal information corresponding to piano notes in the frequency spectrum. We use the phase space reconstruction method to extract the nonlinear feature parameters in the note audio and use some of the parameters as the training set to construct the support vector machine (SVM) classifier and the other part as the test set to test the recognition effect. Therefore, the method of adaptive signal decomposition and SVM is introduced into the signal preprocessing link, and the corresponding recognition process is established. In order to improve the performance of the support vector machine, the article uses measurement learning method to obtain the measurement learning and uses the measurement learning to replace the Euclidean distance of the Gaussian kernel function of the support vector machine. The SVM method of adaptive signal decomposition and the SVM method of principal component analysis are introduced into the preprocessing process of the note signal, and then the preprocessed signal is reconstructed in phase space, and the corresponding recognition process is established. The method of directly reconstructing the phase space of the original signal has higher accuracy and can be applied to the note recognition of continuous music segments. The final experimental results show that, compared with the current popular piano score recognition algorithm, the recognition accuracy of the proposed piano score recognition algorithm is improved by 3.5% to 12.2%.