Introduction to SIMSSA (Single Interface for Music Score Searching and Analysis)

Fujinaga, Ichiro; Hankinson, Andrew; Cumming, Julie E.

doi:10.1145/2660168.2660184

Cited by 14 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the context of cultural preservation and dissemination, the Single Interface for Music Score Searching and Analysis (SIMSSA) project [20] aims at not only making the digital images of ancient scores available to the public but, also, analyzing their structure to make them accessible. Thus, the interpretation of the meaning of musical symbols is of great importance and so is the correct identification of their location with respect to their corresponding staff.…”

Section: Context: Simssa Projectmentioning

confidence: 99%

Automatic Staff Reconstruction within SIMSSA Project

Tardón

Barbancho

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The automatic analysis of scores has been a research topic of interest for the last few decades and still is since music databases that include musical scores are currently being created to make musical content available to the public, including scores of ancient music. For the correct analysis of music elements and their interpretation, the identification of staff lines is of key importance. In this paper, a scheme to post-process the output of a previous musical object identification system is described. This system allows the reconstruction by means of detection, tracking and interpolation of the staff lines of ancient scores from the digital Salzinnes Database. The scheme developed shows a remarkable performance on the specific task it was created for.

show abstract

Section: Context: Simssa Projectmentioning

confidence: 99%

Automatic Staff Reconstruction within SIMSSA Project

Tardón

Barbancho

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…The preservation of the musical heritage over the centuries makes it possible to go deeper into the study of certain artistic and cultural paradigms. Most of this heritage is stored in cathedrals, archives and music libraries [11]. In addition to issues related to the ownership of the sources, this storage allows the physical preservation of the sources over time; in turn, it also severely limits the access for study and analysis.…”

Section: Introductionmentioning

confidence: 99%

Hybrid hidden Markov models and artificial neural networks for handwritten music recognition in mensural notation

Calvo-Zaragoza

Toselli

Vidal

2019

Pattern Anal Applic

View full text Add to dashboard Cite

In this paper we present a hybrid approach using Hidden Markov Models (HMM) and Artificial Neural Networks to deal with the task of Handwritten Music Recognition in Mensural notation. Previous works have shown that the task can be addressed with Gaussian density HMMs that can be trained and used in an end-to-end manner; that is, without prior segmentation of the symbols. However, the results achieved using that approach are not sufficiently accurate to be useful in practice. In this work we hybridize HMMs with deep Multi-Layer Perceptrons (MLP), which lead to remarkable improvements in optical symbol modeling. Moreover, this hybrid architecture maintains important advantages of HMMs such as the ability of properly modeling variable-length symbol sequences through segmentation-free training, and the simplicity and robustness of combining optical models with N-gram language models, which provide statistical a priori information about regularities in musical symbol concatenation observed in the training data. The results obtained with the proposed hybrid MLP-HMM approach outperform previous works by a wide margin, achieving symbol-level error rates around 26%, as compared with about 40% reported in previous works.

show abstract

“…In recent years, diverse initiatives have been launched to digitize musical heritage in the written form, such as the The Digital Image Archive of Medieval Music project [1] on the academic side, or at the same time the crowd-sourced International Music Score Library Project (IMSLP) repository of public-domain and openly available music [2] which has grown to become a primary provider of sheet music worldwide. However, making not only the digital images of all these compositions, but also their structured representation accessible at scale, as attempted e.g., by the Single Interface for Music Score Searching and Analysis (SIMSSA) project [3], would constitute a breakthrough in interacting with written music, and making it accessible to both the professional and the general public in previously unseen ways: content-based search in large sheet music libraries including cross-modal retrieval, digital musicology at scale and with access to structured representations of music that only exists in written form, renotation of early notation to modern notation, manuscript transcription and part-matching to directly cut costs of music directors and composers. These (and more) applications have been envisioned in OMR literature for a long time [4,5]; however, results have not been forthcoming [6].…”

Section: Introductionmentioning

confidence: 99%

A Baseline for General Music Object Detection with Deep Learning

2018

View full text Add to dashboard Cite

Deep learning is bringing breakthroughs to many computer vision subfields including Optical Music Recognition (OMR), which has seen a series of improvements to musical symbol detection achieved by using generic deep learning models. However, so far, each such proposal has been based on a specific dataset and different evaluation criteria, which made it difficult to quantify the new deep learning-based state-of-the-art and assess the relative merits of these detection models on music scores. In this paper, a baseline for general detection of musical symbols with deep learning is presented. We consider three datasets of heterogeneous typology but with the same annotation format, three neural models of different nature, and establish their performance in terms of a common evaluation standard. The experimental results confirm that the direct music object detection with deep learning is indeed promising, but at the same time illustrates some of the domain-specific shortcomings of the general detectors. A qualitative comparison then suggests avenues for OMR improvement, based both on properties of the detection model and how the datasets are defined. To the best of our knowledge, this is the first time that competing music object detection systems from the machine learning paradigm are directly compared to each other. We hope that this work will serve as a reference to measure the progress of future developments of OMR in music object detection.

show abstract

Introduction to SIMSSA (Single Interface for Music Score Searching and Analysis)

Cited by 14 publications

References 3 publications

Automatic Staff Reconstruction within SIMSSA Project

Automatic Staff Reconstruction within SIMSSA Project

Hybrid hidden Markov models and artificial neural networks for handwritten music recognition in mensural notation

A Baseline for General Music Object Detection with Deep Learning

Contact Info

Product

Resources

About