Music4All: A New Music Database and Its Applications

One of the goals of the music information retrieval (MIR) community is to research new methods and create new systems that can efficiently and effectively retrieve and recommend songs from large databases of music content. Despite the volume of research in the area, there is a lack of music databases to support these works, i.e. databases that comply with some quite desirable requirements for the development of researches, such as: a huge amount of music pieces, the audio signal availability and a great diversity of audio attributes. In order to contribute to the MIR community, we present Music4All, a new music database which contains metadata, tags, genre information, 30-seconds audio clips, lyrics, and so on. Additionally, we also exemplify some MIR tasks that may benefit from our database and compare it with other databases proposed in the literature. To request the Music4All database, send an e-mail to contact4music4all@gmail.com.

Music Information Retrieval (MIR) is an interdisciplinary research area that covers automated extraction of information from audio signals, music databases and services enabling the indexed information searching. In the early stages the primary focus of MIR was on music information through Query-by-Humming (QBH) applications, i.e. on identifying a piece of music by singing (singing/whistling), while more advanced implementations supporting Query-by-Example (QBE) searching resulted in names of audio tracks, song identification, etc. Both QBH and QBE required several steps, among others an optimized signal parametrization and the soft computing approach. Nowadays, MIR is associated with research based on the content analysis that is related to the retrieval of a musical style, genre or music referring to mood or emotions. Even though, this type of music retrieval called Query-by-Category still needs feature extraction and parametrization optimizing, but in this case search of global online music systems and services applications with their millions of users is based on statistical measures. The paper presents details concerning MIR background and answers a question concerning usage of soft computing versus statistics, namely: why and when each of them should be employed.

Towards improving the performance in various music information processing tasks, recent studies exploit different modalities able to capture diverse aspects of music. Such modalities include audio recordings, symbolic music scores, mid-level representations, motion, and gestural data, video recordings, editorial or cultural tags, lyrics and album cover arts. This paper critically reviews the various approaches adopted in Music Information Processing and Retrieval and highlights how multimodal algorithms can help Music Computing applications. First, we categorize the related literature based on the application they address. Subsequently, we analyze existing information fusion approaches, and we conclude with the set of challenges that Music Information Retrieval and Sound and Music Computing research communities should focus in the next years.

Musical themes are essential elements in Western classical music. In this paper, we present the Musical Theme Dataset (MTD), a multimodal dataset inspired by “A Dictionary of Musical Themes” by Barlow and Morgenstern from 1948. For a subset of 2067 themes of the printed book, we created several digital representations of the musical themes. Beyond graphical sheet music, we provide symbolic music encodings, audio snippets of music recordings, alignments between the symbolic and audio representations, as well as detailed metadata on the composer, work, recording, and musical characteristics of the themes. In addition to the data, we also make several parsers and web-based interfaces available to access and explore the different modalities and their relations through visualizations and sonifications. These interfaces also include computational tools, bridging the gap between the original dictionary and music information retrieval (MIR) research. The dataset is of relevance for various subfields and tasks in MIR, such as cross-modal music retrieval, music alignment, optical music recognition, music transcription, and computational musicology.

In this paper, we address the challenge of identifying music suitable to accompany typical daily activities. We first derive a list of common activities by analyzing social media data. Then, an automatic approach is proposed to find music for these activities. Our approach is inspired by our experimentally acquired findings (a) that genre and instrument information, i.e., as appearing in the textual metadata, are not sufficient to distinguish music appropriate for different types of activities, and (b) that existing content-based approaches in the music information retrieval community do not overcome this insufficiency. The main contributions of our work are (a) our analysis of the properties of activity-related music that inspire our use of novel high-level features, e.g., drop-like events, and (b) our approach's novel method of extracting and combining low-level features, and, in particular, the joint optimization of the time window for feature aggregation and the number of features to be used. The effectiveness of the approach method is demonstrated in a comprehensive experimental study including failure analysis.

This paper introduces the Raga Based Music Classification as a part of Music Information Retrieval (MIR) systems for retrieving musical information. The music has been more than just a sound that entertains us. MIR users like musicology researchers, musicians, music learners, music therapists, etc., require not just the sound but the actual strength of the music that controls our body, motivates us, cures mental illness, etc. The backbone of any form of music is its raga. A raga is a particular combination of notes with certain laws which, when carefully observed, preserves and safeguards their integrity and create wonders in music. The existing MIR systems and audio search engines concentrate on content based audio mining and not ragas. This paper discusses the classification of ragas and how it differs in Carnatic, Hindustani and Western musical forms. It also describes the various features that can be extracted from an audio data to represent a raga. Finally, we propose a system architecture to perform raga based classification of music.

Genetic algorithms have been introduced to the field of media segmentation including image, video, and also music segmentation since segmentation problems usually have complex fitness landscapes. Music segmentation can provide insight into the structure of a music composition so it is an important task in music information retrieval (MIR). The authors have already presented the application of genetic algorithms for the music segmentation problem in an earlier paper. This paper focuses on the optimization of parameter settings for genetic algorithms in the field of MIR as well as on the comparison of their results.

Over the years, Music Information Retrieval (MIR) has proposed various models pretrained on large amounts of music data. Transfer learning showcases the proven effectiveness of pretrained backend models with a broad spectrum of downstream tasks, including auto-tagging and genre classification. However, MIR papers generally do not explore the efficiency of pretrained models for Music Recommender Systems (MRS). In addition, the Recommender Systems community tends to favour traditional end-to-end neural network learning over these models. Our research addresses this gap and evaluates the applicability of six pretrained backend models (MusicFM, Music2Vec, MERT, EncodecMAE, Jukebox, and MusiCNN) in the context of MRS. We assess their performance using three recommendation models: K-nearest neighbours (KNN), shallow neural network, and BERT4Rec. Our findings suggest that pretrained audio representations exhibit significant performance variability between traditional MIR tasks and MRS, indicating that valuable aspects of musical information captured by backend models may differ depending on the task. This study establishes a foundation for further exploration of pretrained audio representations to enhance music recommendation systems.

We present the open-source implementation of the first fully automatic and comprehensive DJ system, able to generate seamless music mixes using songs from a given library much like a human DJ does.The proposed system is built on top of several enhanced music information retrieval (MIR) techniques, such as for beat tracking, downbeat tracking, and structural segmentation, to obtain an understanding of the musical structure. Leveraging the understanding of the music tracks offered by these state-of-the-art MIR techniques, the proposed system surpasses existing automatic DJ systems both in accuracy and completeness. To the best of our knowledge, it is the first fully integrated solution that takes all basic DJing best practices into account, from beat and downbeat matching to identification of suitable cue points, determining a suitable cross-fade profile and compiling an interesting playlist that trades off innovation with continuity.To make this possible, we focused on one specific sub-genre of electronic dance music, namely Drum and Bass. This allowed us to exploit genre-specific properties, resulting in a more robust performance and tailored mixing behavior.Evaluation on a corpus of 160 Drum and Bass songs and an additional hold-out set of 220 songs shows that the used MIR algorithms can annotate 91% of the songs with fully correct annotations (tempo, beats, downbeats, and structure for cue points). On these songs, the proposed song selection process and the implemented DJing techniques enable the system to generate mixes of high quality, as confirmed by a subjective user test in which 18 Drum and Bass fans participated.

Nowadays, the term cover song (or simply cover) can mean any new version, performance, rendition, or recording of a previously recorded track. Cover song identification is a task that has received increased popularity in the Music Information Retrieval (MIR) community in recent years, as it provides a direct and objective way for evaluating music similarity. In this paper, we propose a new method for determining the similarity between tonal sequences and, therefore, for identifying cover songs. This is based on a novel chroma similarity measure, and on a newly developed dynamic programming local alignment technique. Results confirm that the performance of the proposed system is significantly superior to other state-of-the-art approaches (more than 57% better).

The article describes the project on music information retrieval that has been carried out at the University of Padova, Italy. The research work has been characterized by the synergy of the modular integration of sound techniques of melody processing and of statistical information retrieval. After illustrating the background from which the project has originated, we describe the complete process, from methodology design through evaluation and system implementation. Conclusions, impacts on research in music information retrieval, and future directions are also described.

The field of Music Information Retrieval is still very immature although it has been addressed by a substantial number of research projects over past three decades. Many problems are faced in music information retrieval due to the nature of music itself. In this paper, the basic representation of audio and video are discussed along with the challenges of music retrieval. The need for music information is discussed using the statistical survey. The paper challenges the common assumption that searching on the pitch alone is satisfactory and discusses the other features which can aid in searching. This assumption may indeed be right for monophonic music but it is insufficient for polyphonic music. Even in monophonic music the possibility of faulty results can’t be ignored.

Singing voice detection (SVD), to recognize vocal parts in the song, is an essential task in music information retrieval (MIR). The task remains challenging since singing voice varies and intertwines with the accompaniment music, especially for some complicated polyphonic music such as choral music recordings. To address this problem, we investigate singing voice detection while discarding the interference from the accompaniment. The proposed SVD has two steps: i. The singing voice separation (SVS) technique is first utilized to filter out the singing voice’s potential part coarsely. ii. Upon the continuity of vocal in the time domain, Long-term Recurrent Convolutional Networks (LRCN) is used to learn compositional features. Moreover, to eliminate the outliers, we choose to use a median filter for time-domain smoothing. Experimental results show that the proposed method outperforms the existing state-of-the-art works on two public datasets, the Jamendo Corpus and the RWC pop dataset.KeywordsSinging voice detectionVocal detectionSinging voice separationMusic information retrieval

With continued growth of music content available on the Internet, music information retrieval has attracted increasing attention. An important challenge for music searching is its ability to support both keyword and content based queries efficiently and with high precision. In this paper, we present a music query system - QueST (Query by acouStic and Textual features) to support both keyword and content based retrieval in large music databases. QueST has two distinct features. First, it provides new index schemes that can efficiently handle various queries within a uniform architecture. Concretely, we propose a hybrid structure consisting of Inverted file and Signature file to support keyword search. For content based query, we introduce the notion of similarity to capture various music semantics like melody and genre. We extract acoustic features from a music object, and map it to multiple high-dimension spaces with respect to the similarity notion using PCA and RBF neural network. Second, we design a result fusion scheme, called the Quick Threshold Algorithm, to speed up the processing of complex queries involving both textual and multiple acoustic features. Our experimental results show that QueST offers higher accuracy and efficiency compared to existing algorithms.

Music Information Retrieval (MIR) is a crucial topic in the domain of information retrieval. According to major characteristics of music, Query-by-Humming system retrieves interesting music by finding melody that contains similar or equal melody to the humming query. Basing on the designed fuzzy inference model a novel Query-by-Humming/Singing system is proposed to extract pitch contour information from WAV and MIDI files in this paper. To verify the effectiveness of the presented work, the MIREX QBSH Database is employed as our experimental database and a large amount of human vocal data is used as query to test the robustness of MIR. Then, the Longest Common Subsequence (LCS) is served as an approximate matching algorithm to identify the most related top 5 music as an evaluation standard for the system. Experimental results show that the proposed system achieves 85% accuracy in the top 5 retrievals.