Musical Sequences Research Articles

Traitement de l’ambiguïté syntaxique et sémantique en TA neuronale : analyse de la traduction de l’anglais vers le français, l’espagnol et l’italien

Syntactic and Semantic Ambiguity Processing in Neural MT from English to French, Spanish and Italian
 Despite recent advances in artificial intelligence, human translators outperform MT for at least three types of tasks: identifying referents in anaphora (especially of the interphrastic kind), resolving semantic ambiguity (which is mainly due to polysemy or homonymy), and resolving syntactic ambiguity (especially with poorly inflected source languages such as English). Using the results obtained by two freely available online machine translation programs, Google Translate and DeepL, we examine how these two types of ambiguity are processed in translation from English into French, Spanish and Italian. Our results show that the two programs perform well overall in resolving the simplest cases of syntactic ambiguity, with difficulties arising more frequently for noun phrases featuring atypical syntactic divisions and rarely used collocations. MT output for ambiguous structures involving verb roots followed by the –ING morpheme (flying planes, growing pains) is studied, as well as syntactic structures in which two or more nouns are preceded by one or more adjectives. MT handles relatively well the longest of those structures (ADJ ADJ N N N N), probably because their subsets are part of the bilingual or target language monolingual corpora that underlie MT systems. Structures involving head modification and coordination (ADJ N AND N) are also known to pose problems for MT and human translators alike. But since many of the most frequent N AND N structures involve cohyponyms (men and women, brothers and sisters), antonyms (rights and duties, costs and benefits) or near- synonyms (aid and advice), their translation as a whole unit generally triggers the choice of correct syntact dependencies in translation. Structures in which the adjective only modifies the first noun (fresh air and exercise, social sciences and humanities) are much less frequent and are also probably translated as a whole unit. Structures involving premodification, coordination and post-modification may give rise to four distinct types of structures depending on whether long-range dependencies apply (detailed [knowledge and understanding] of the IT industry, [ethnic group] and [place of birth], invaluable [context and [source of information], [close friend] and confidant] of Mr Jones. Structures in which both long-range dependencies apply (integrated prevention and control of pollution) are the ones which most frequently cause errors for MT. Semantic ambiguity cases have been processed with increasing success by MT, especially when collocates vary widely for the main two meanings of homonyms (a well-known example is the word pen). Processing polysemy (for instance the medical use of conditions in pre-existing conditions) is a bit more of a challenge for MT. Other cases involving concentration of several polysemic terms in the same sentence (Changing the placement of beams relative to the staff involves changing the direction of the stems in the beam) also create difficulties for MT when the polysemic terms are used without any of their usual collocates (here in the specialised field of musical edition). Homonymy cases involving grammatical category changes (N-to-V or V-to-N conversion) seem to continue to pose the most difficulties to neural MT, despite increasing consideration of intra- and extraphrastic context. Potentially ambiguous word sequences (treatment increase in as the daily dose and duration of treatment increase), which were processed incorrectly before neuronal MT, are now correctly translated. But word sequences in which one word belongs to a part of speech which is not the most commonly used one (e.g. the noun remains in what remains can be considered) may cause occasional errors. Several examples that involve the verb founder are studied, and they frequently trigger translation of the noun in all three Romance languages (or translations of the verbs find or found due to incorrect segmentation).

Educational Evaluation of Piano Performance by the Deep Learning Neural Network Model

In recent years, the piano education industry has occupied a huge market. However, the automatic evaluation function of piano performance has shortcomings in existing piano education products. Deep learning (DL) algorithm and the recurrent neural network (RNN) structure can help in automatics evaluation function of the piano performance. This paper proposes a Musical Instrument Digital Interface (MIDI) piano evaluation scheme based on the RNN structure and the Spark computing engine using the Deeplearning4J DL framework. The Deeplearning4J framework can run on the Java Virtual Machine; therefore, the entire system does not require cross-platform development. The Spark distributed computing engine realizes parallelization in music data preprocessing, feature extraction, and model training. Combined with the training user interface (UI) provided by the Deeplearning4J, it can improve developmental efficiency. Additionally, the RNN parameters are analyzed. The results demonstrate that the error value of the three-layer RNN structure is smaller than other closest rivals’ techniques. In particular, few piano training institutions and MIDI website datasets are used as the basis, and the experimental samples are collected. The neural network is trained, and the performance of the evaluation model is tested. The results show that the evaluation outcomes of the designed performance evaluation model for the piano are fundamentally consistent with the real levels of the players with assured feasibility; after 3k times of the training periods, the error of the RNN model is close to 0.01 and the network converges.

Correlation between Acoustic Analysis and Psycho-Acoustic Evaluation of Violins

This paper presents the results of an experimental study performed on seven violins obtained from a top plate made of resonance spruce and a back plate made of curly maple. Each pair of plates had a different modification to its thickness profile. Some were thickened and others were thinned compared to the classical thickness profile. Then, a soloist played a musical sequence on each violin and the acoustic signals were recorded. The sound quality of the signals was evaluated with a psycho-acoustic evaluation based on a blind questionnaire completed by listeners. It turned out that: (1) respondents with more musical experience (especially those with over 26 years of experience) were more demanding in assessing sound clarity and offered the widest range of scores in assessing this quality; (2) the musical experience of the respondents influenced to the highest degree the appreciation of the warm sound quality; (3) the scores for the violins with thinned plates were weaker, especially according to the psycho-acoustic analysis; and (4) the highest score was obtained by the violin with the thickest plates, which can be correlated with the two dominant frequencies extracted from the FFT analysis, whose values coincide with the frequencies of the B1− and B1+ modes.

Band-in-a-Box-a program to create compositions in genres of popular music

The goal of the work. The purpose of the article is to disclose new tools and methods of using computer technologies in modern musical practice on the example of a description of work and ample opportunities for an arrangement of the Band-in-A-BOX Senecrent. The research methodology is to identify and present practical methods of working in the Band-in-A-Box Seckwowner at the main stages of functioning. The scientific novelty of the work is to reveal the palette of the contemporary Band-in-A-Box sequencer when arranging musical works with the help of one of the most powerful modern music editors. The use of Band-in-A-Box Seneseor increases the interest of modern youth in quality musical training, as well as expanding the palette of opportunities for composers, arrangers, sound directors and beginners musicians. Conclusions. Music computer technologies are a new field of knowledge that is constantly developing. It synthesizes technology and art, and these are two poles that are constantly moving and improving tools for creativity, learning and research. The dynamic nature of these processes is associated with the continuous restoration of scientific and technological progress. Band-in-a- Box music sequoter is another modern advanced computer program that offers advanced technologies for creative experiments in creating and arranging musical compositions. The program has many other useful features, a developed menu system, dialogs that allow you to adjust literally every parameter of arrangement and sound synthesis. The number of finished styles is constantly increasing. The program is also interesting because it seems to generate all those knowledge about the ability to perform on the synthesizer when applying the function of automatic companion. Keywords: musical sevener, computer arrangement, Midi instruments, composer, sound engineer.

Synchronization during Improvised Active Music Therapy in clients with Parkinson’s disease

ABSTRACT Introduction The purpose of this manuscript is to report on the finding of asynchrony measures during Improvised Active Music Therapy (IAMT) sessions with individuals with Parkinson’s disease (PD). Method In this single subject multiple baseline design across subjects, the study measured asynchrony of three right-handed participants with PD while playing uninterrupted improvised music on a simplified electronic drum-set. During baseline, the music therapist played rhythms with lowto moderate density of syncopation. During treatment, the music therapist introduced rhythms with moderate to high density of syncopation. The music content of the sessions was transformed into digital music using Musical Instrument Digital Interface (MIDI). MIDI data were analyzed to determine participants’ and the music therapist’s asynchrony (on acoustic guitar) during baseline and treatment conditions. Results The results of this manuscript suggest that all participants exhibited total negative mean asynchrony and in that the music therapist exhibited total positive mean asynchrony scores within and across conditions. All participants also demonstrated score fluctuation in left foot and right foot as compared to upper extremity within and across conditions. Discussion Overall, participants showed their ability to synchronize to the music produced by the music therapist throughout conditions by demonstrating anticipation. Also, participants demonstrated some difficulty while synchronizing with lower extremity. Music therapy clinicians might benefit from knowledge of their own tempo inconsistencies to be able to synchronize with clients more effectively. More research is required to identify commonalities and differences in music synchronization measures between individuals with PD and healthy individuals during IAMT sessions.

Music Genre Classification Based on Deep Learning

Human music life can be traced back to ancient times. The music art of human society is rich and colorful, which makes the music classification unable to classify efficiently and accurately. Moreover, the classification has become a daunting task. On this basis, this paper studies the method of deep learning for processing music classification. Not only is the design structure of music signal channel classified, but also all connected neural networks associated with the music are investigated to design an appropriate network model. According to different music sequence measurements, the feature sequence mechanism of music design feedback optimization is also investigated. The type probabilities of different calculated orbits are measured by softmax activation function, and the function value of cross loss is obtained. Finally, an Adam optimization algorithm is used as the optimization algorithm of the proposed network model. Subsequently, an independent adaptive learning planning rate is designed. By adjusting the network parameters, the first- and second-order estimates of the calculated gradient are classified. The experimental outcomes prove that the anticipated method can meritoriously increase the correctness of music classification and is helpful for music channel classification. Moreover, we also observed that the number of neurons in the network has also a significant impact over the training and testing errors.

Band-in-a-Box – a program to create compositions in genres of popular music (Part 1).

The goal of the work. The purpose of the article is to disclose new tools and methods of using computer technologies in modern musical practice on the example of a description of work and ample opportunities for an arrangement of the Band-in-A-Box Senecrent. The research methodology is to identify and present practical methods of working in the Band-in-A-Box Seckwowner at the main stages of functioning. The scientific novelty of the work is to reveal the palette of the contemporary Band-in-A-Box sequencer when arranging musical works with the help of one of the most powerful modern music editors. The use of Band-in-A-Box Seneseor increases the interest of modern youth in quality musical training, as well as expanding the palette of opportunities for composers, arrangers, sound directors and beginners musicians. Conclusions. Music computer technologies are a new field of knowledge that is constantly developing. It synthesizes technology and art, and these are two poles that are constantly moving and improving tools for creativity, learning and research. The dynamic nature of these processes is associated with the continuous restoration of scientific and technological progress. Band-in-a- Box music sequoter is another modern advanced computer program that offers advanced technologies for creative experiments in creating and arranging musical compositions. The program has many other useful features, a developed menu system, dialogs that allow you to adjust literally every parameter of arrangement and sound synthesis. The number of finished styles is constantly increasing. The program is also interesting because it seems to generate all those knowledge about the ability to perform on the synthesizer when applying the function of automatic companion.
 Key words: musical sevener, computer arrangement, Midi instruments, composer, sound engineer.

Enhanced Evaluation Method of Musical Instrument Digital Interface Data based on Random Masking and Seq2Seq Model

With developments in artificial intelligence (AI), it is possible for novel applications to utilize deep learning to compose music by the format of musical instrument digital interface (MIDI) even without any knowledge of musical theory. The composed music is generally evaluated by human-based Turing test, which is a subjective approach and does not provide any quantitative criteria. Therefore, objective evaluation approaches with many general descriptive parameters are applied to the evaluation of MIDI data while considering MIDI features such as pitch distances, chord rates, tone spans, drum patterns, etc. However, setting several general descriptive parameters manually on large datasets is difficult and has considerable generalization limitations. In this paper, an enhanced evaluation method based on random masking and sequence-to-sequence (Seq2Seq) model is proposed to evaluate MIDI data. An experiment was conducted on real MIDI data, generated MIDI data, and random MIDI data. The bilingual evaluation understudy (BLEU) is a common MIDI data evaluation approach and is used here to evaluate the performance of the proposed method in a comparative study. In the proposed method, the ratio of the average evaluation score of the generated MIDI data to that of the real MIDI data was 31%, while that of BLEU was 79%. The lesser the ratio, the greater the difference between the real MIDI data and generated MIDI data. This implies that the proposed method quantified the gap while accurately identifying real and generated MIDI data.

Author Submission Guidelines

Author Submission Guidelines

MIDI in Formal Music Education: Reflections on the Application of MIDI-Oriented Tools in Traditional Teaching and Learning Processes

Since 1983, with the release of the MIDI protocol, new resources have been developed for musical editing, composition, arrangement and performance. Due to the growing expansion of computers’ storage and processing capacities, it has also been possible to increase the quality and specificity of sample libraries. In this context, the following work reflects on possible educational impacts of the research which investigate different audiences’ perceptions regarding audios recorded by drummers’ performances and by MIDI tools. Supported by the respondents’ perceptions, the general aim of this paper is to reflect on the challenges for the application of MIDI-oriented approaches in formal teaching and learning music processes. Excerpted from this, four specific aims can be drawn: 1) to present the basic elements of sampling and MIDI protocol; 2) to systematically and pedagogically describe the procedures employed in the process of sequencing the selected drummers’ performances; 3) to apply quality-assessment questionnaires for the sequencing-generated audios; 4) to reflect on the connections between the questionnaires’ results and the use of MIDI in formal music education contexts. Pursuing these aims, the current investigation employs qualitative and quantitative methods to gather the data, to analyze the materials and to develop the knowledge that will guide the proposed discussions. It is defended that the employment of MIDI resources in music education can be beneficial not only for the development of knowledge connected with digital and modern technologies but also for the improvement of traditionally pursued music competences.

An Improved Music Composing Technique Based on Neural Network Model

Traditionally, music was considered an analog signal that had to be made by hand. In recent decades, music has been highlighted by technology that can autonomously compose a suite of music without any human interaction. To achieve this goal, this article suggests an autonomous music composition technique based on long short-term memory recurrent neural networks. Firstly, the music collection is split into music sequences based on unit time, and the Meier cepstrum coefficients of music audio are retrieved as features during music preprocessing. Secondly, the training samples composed of feature vectors processed by data were trained and predicted by short- and long-term memory models. Finally, the generated music sequence is spliced and fused to get new music. This article designs and performs experiments to demonstrate that our results are promising. From experimental results, this work gained that our model has the maximum accuracy of 99% and the lowest loss rate of 0.03.

Evaluation Strategy of the Piano Performance by the Deep Learning Long Short-Term Memory Network

With the development of society and the progress of technology, the piano education industry has a large market. In view of the problem of high payment fees in the piano education industry, the scientific and automatic nature of piano performance evaluation has attracted people’s attention. However, since most of the piano performance evaluation schemes are based on rules, the continuity of the piano music and the accuracy of playing are ignored. Therefore, the purpose is to design a scientific piano performance evaluation scheme that can play a certain role in the sustainable development of the piano education industry. Firstly, long short-term memory in deep learning is explored. Secondly, the musical characteristics of piano performance are analyzed according to the musical instrument digital interface. The piano music features are extracted, and a long short-term memory-based musical instrument digital interface piano performance evaluation model is constructed. Finally, it analyzes the number of hidden layers implemented in the long short-term memory model for piano performance evaluation. The accuracy of piano performance evaluation under different models is analyzed. Under the bidirectional long short-term memory network model, different piano performance levels are evaluated to realize the study of piano performance evaluation strategies. Compared with the accuracy of the recurrent neural network and the long short-term memory model with different hidden layers, the bidirectional long short-term memory model has the highest test accuracy, with an average of 69.78%. When the hidden layer of the bidirectional long short-term memory model is 3, the loss function L value is the smallest, which is 0.11. Different levels of piano skills are evaluated, and the results of the systematic evaluation are consistent with the performance of different levels. This shows that the BLSM model is feasible for the piano performance evaluation strategy system. This study not only conducts an in-depth analysis of the deep learning long short-term memory model but also proposes a long short-term memory-based musical instrument digital interface piano performance evaluation model. Additionally, the flaws such as the incomplete consideration of musical continuity and expressiveness when evaluating piano performance pieces have been compensated. Finally, through different model validations, the bidirectional long short-term memory model is concluded with good accuracy in piano performance evaluation. These conclusions provide theoretical research and practical significance for the accuracy of piano performance evaluation.

Design of Neural Network Model for Cross-Media Audio and Video Score Recognition Based on Convolutional Neural Network Model.

In this paper, the residual convolutional neural network is used to extract the note features in the music score image to solve the problem of model degradation; then, multiscale feature fusion is used to fuse the feature information of different levels in the same feature map to enhance the feature representation ability of the model. A network composed of a bidirectional simple loop unit and a chained time series classification function is used to identify notes, parallelizing a large number of calculations, thereby speeding up the convergence speed of training, which also makes the data in the dataset no longer need to be strict with labels. Alignment also reduces the requirements on the dataset. Aiming at the problem that the existing cross-modal retrieval methods based on common subspace are insufficient for mining local consistency within modalities, a cross-modal retrieval method fused with graph convolution is proposed. The K-nearest neighbor algorithm is used to construct modal graphs for samples of different modalities, and the original features of samples from different modalities are encoded through a symmetric graph convolutional coding network and a symmetric multilayer fully connected coding network, and the encoded features are fused and input. We jointly optimize the intramodal semantic constraints and intermodal modality-invariant constraints in the common subspace to learn highly locally consistent and semantically consistent common representations for samples from different modalities. The error value of the experimental results is used to illustrate the effect of parameters such as the number of iterations and the number of neurons on the network. In order to more accurately illustrate that the generated music sequence is very similar to the original music sequence, the generated music sequence is also framed, and finally the music sequence spectrogram and spectrogram are generated. The accuracy of the experiment is illustrated by comparing the spectrogram and the spectrogram, and genre classification predictions are also performed on the generated music to show that the network can generate music of different genres.

Deep Learning-Based Music Quality Analysis Model.

In order to build an efficient and effective deep much quality recognition model, a decision fusion method by leveraging the advantages of shallow learning and deep learning is formulated. In the literature, shallow learning is a traditional music-related quality recognition method, that is, artificial statistical feature extraction and recognition are designed. Meanwhile, our deep learning module leverages the so-called PCANET network to implement the feature extraction process, and subsequently takes the spectrogram describing the music-related information as the network input. First, a variety of task classifications for the music signal problem are divided. Afterward, the optimization and adoption of deep learning in the two major problems of music feature extraction and sequence modeling are introduced. Finally, a music application is presented to illustrate the practical application of deep learning in music quality evaluation. The shallow learning features and deep learning features are seamlessly combined into the SVM model for music quality modeling, based on which differential voting mechanisms are leveraged to realize the fusion of decision-making layers. Extensive experimental results have shown that the music quality recognition rate by this method can be significantly improved on our own compiled library and the Berlin database. Besides, it exhibits obvious advantages compared with the competitors.

A Fuzzy Multicriteria Assessment Mechanism towards Musical Courses Using Deep Learning

Nowadays, the musical courses have been quite prevalent spiritual activities in online or offline scenarios. However, the teaching quality is diverse and cannot be easily assessed by general nonprofessional audience. Limited by the amount of experts, it is supposed to investigate intelligent mechanisms that can automatically assess the teaching quality of musical courses. To deal with such issue, the combination of artificial intelligence and conventional music knowledge acts as a promising way. In this work, a fuzzy multicriteria assessment mechanism is used towards musical courses with the use of a typical deep learning model: convolutional neural network (CNN). Specifically, note that features inside the musical symbol sequences are expected to be extracted by residual CNN structure. Next, multilevel features inside the musical notes are further fused with neural computing structure, so that feature abstraction of initial musical objects can be further improved. On this basis, notes can be identified with use of bidirectional recurrent unit structure in order to speed up fitting efficiency of the whole assessment framework. Comprehensive experimental analysis is conducted by comparing the proposed method with several baseline methods, showing a good performance effect of the proposal.

COSMOS: Computational Shaping and Modeling of Musical Structures

This position paper makes the case for an innovative, multi-disciplinary methodological approach to advance knowledge on the nature and work of music performance, driven by a novel experiential perspective, that also benefits analysis of electrocardiographic sequences. Music performance is considered by many to be one of the most breathtaking feats of human intelligence. It is well accepted that music performance is a creative act, but the nature of its work remains elusive. Taking the view of performance as an act of creative problem solving, ideas in citizen science and data science, optimization, and computational thinking provide means through which to deconstruct the process of music performance in scalable ways. The method tackles music expression's lack of notation-based data by leveraging listeners' perception and experience of the structures elicited by the performer, with implications for data collection and processing. The tools offer ways to parse a musical sequence into coherent structures, to design a performance, and to explore the space of possible interpretations of the musical sequence. These ideas and tools can be applied to other music-like sequences such as electrocardiographic recordings of arrhythmias (abnormal heart rhythms). Leveraging musical thinking and computational approaches to performance analysis, variations in expressions of cardiac arrhythmias can be more finely characterized, with implications for tailoring therapies and stratifying heart rhythm disorders.

The Classification of Music and Art Genres under the Visual Threshold of Deep Learning.

Wireless networks are commonly employed for ambient assisted living applications, and artificial intelligence-enabled event detection and classification processes have become familiar. However, music is a kind of time-series data, and it is challenging to design an effective music genre classification (MGC) system due to a large quantity of music data. Robust MGC techniques necessitate a massive amount of data, which is time-consuming, laborious, and requires expert knowledge. Few studies have focused on the design of music representations extracted directly from input waveforms. In recent times, deep learning (DL) models have been widely used due to their characteristics of automatic extracting advanced features and contextual representation from actual music or processed data. This paper aims to develop a novel deep learning-enabled music genre classification (DLE-MGC) technique. The proposed DLE-MGC technique effectively classifies the music genres into multiple classes by using three subprocesses, namely preprocessing, classification, and hyperparameter optimization. At the initial stage, the Pitch to Vector (Pitch2vec) approach is applied as a preprocessing step where the pitches in the input musical instrument digital interface (MIDI) files are transformed into the vector sequences. Besides, the DLE-MGC technique involves the design of a cat swarm optimization (CSO) with bidirectional long-term memory (BiLSTM) model for the classification process. The DBTMPE technique has gained a moderately increased accuracy of 94.27%, and the DLE-MGC technique has accomplished a better accuracy of 95.87%. The performance validation of the DLE-MGC technique was carried out using the Lakh MIDI music dataset, and the comparative results verified the promising performance of the DLE-MGC technique over current methods.

Tension experience induced by tonal and melodic shift at music phrase boundaries

Music tension is a link between music structures and emotions. As music unfolds, developmental patterns induce various emotional experiences, but the relationship between developmental patterns and tension experience remains unclear. The present study compared two developmental patterns of two successive phrases (tonal shift and melodic shift) with repetition condition to investigate the relationship with tension experience. Professional musicians rated on-line felt tension and EEG responses were recorded while listening to music sequences. Behavioral results showed that tension ratings under tonal and melodic shift conditions were higher than those under repetition conditions. ERP results showed larger potentials at early P300 and late positive component (LPC) time windows under tonal shift condition, and early right anterior negativity (ERAN) and LPC under melodic shift condition. ERSP results showed early beta and late gamma power increased under tonal shift condition, theta power decreased and alpha power increased under melodic shift condition. Our findings suggest that developmental patterns play a vital role in tension experiences; tonal shift affects tension by tonal shift detection and integration, while melodic shift affects tension by attentional processing and working memory integration. From the perspective of Event Structure Processing Model, solid evidence was given to specify the time-span segmentation and reduction.

Hear what you feel, feel what you hear: The effect of musical sequences on emotional processing

Music has a unique ability to access affective and motivational systems of the brain. However, there is a gap in research on the association between musical stimuli and their impact on emotional processing, a crucial component for the success of the therapeutic process. The present study thus sought to explore both the capacity of music to access the affective system, to induce emotions, and to change emotional states, as well as to facilitate emotional processing leading to the resolution of emotional distress. Pascual-Leone and Greenberg's validated sequential model of emotional processing in psychotherapy, was used to test this dual capacity. Three musical sequences with distinct components were developed and presented in an online platform. One musical sequence followed the order of the sequential model (first experimental sequence), another musical sequence inverted that same order (second experimental sequence), and the last musical sequence was intended to serve as a baseline (control sequence). All musical sequences, not only led to alterations in participant's emotional states, but also led to an increase of participant's emotional resolution. Some of the results were surprising, since the control sequence also led to an increase of emotional resolution and the first experimental sequence didn't present itself as the winning candidate by leading to a higher emotional resolution. Nevertheless, these surprising results demonstrated that emotional processing could occur under different experiences of music and allow future studies to keep exploring this relationship.

GiantMIDI-Piano: A Large-Scale MIDI Dataset for Classical Piano Music

Symbolic music datasets are important for music information retrieval and musical analysis. However, there is a lack of large-scale symbolic datasets for classical piano music. In this article, we describe the creation of the GiantMIDI-Piano (GP) dataset containing 38,700,838 transcribed notes and 10,855 unique solo piano works composed by 2,786 composers. We extract the names of music works and the names of composers from the International Music Score Library Project (IMSLP). We search and download their corresponding audio recordings from the Internet. We further create a curated subset containing 7,236 works composed by 1,787 composers where the titles of downloaded audio recordings contain the surnames of composers. We apply a convolutional neural network to detect solo piano works. Then, we transcribe those solo piano recordings into Musical Instrument Digital Interface (MIDI) files using a high-resolution piano transcription system. Each transcribed MIDI file contains the onset, offset, pitch, and velocity attributes of piano notes and pedals. GiantMIDI-Piano includes 90% live performance MIDI files and 10% sequence input MIDI files. We analyse the statistics of GiantMIDI-Piano and show pitch class, interval, trichord, and tetrachord frequencies of six composers from different eras to show that GiantMIDI-Piano can be used for musical analysis. We evaluate the quality of GiantMIDI-Piano in terms of solo piano detection F1 scores, metadata accuracy, and transcription error rates. We release the source code for acquiring the GiantMIDI-Piano dataset at <a href="https://github.com/bytedance/GiantMIDI-Piano" target="_blank">https://github.com/bytedance/GiantMIDI-Piano</a>.