International Society for Music Information Retrieval Conference最新文献_第10页

Deconstruct, Analyse, Reconstruct: How to improve Tempo, Beat, and Downbeat Estimation 解构，分析，重构:如何改进节奏，拍和重拍估计

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245498

Sebastian Böck, M. Davies

引用次数: 38

Combining musical features for cover detection 结合音乐特征的掩护检测

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245424

Guillaume Doras, Furkan Yesiler, Joan Serrà, E. Gómez, G. Peeters

引用次数: 8

SuPP & MaPP: Adaptable Structure-Based Representations for MIR Tasks SuPP & MaPP: MIR任务的自适应结构表示

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245438

C. Savard, Erin H. Bugbee, Melissa R. McGuirl, Katherine M. Kinnaird

引用次数: 1

Bistate reduction and comparison of drum patterns 双态还原和鼓型比较

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245432

O. Lartillot, Fred Bruford

引用次数: 0

A Method for Analysis of Shared Structure in Large Music Collections using Techniques from Genetic Sequencing and Graph Theory 基于基因测序和图论的大型音乐合集共享结构分析方法

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245440

F. Thalmann, Kazuyoshi Yoshii, Thomas Wilmering, Geraint A. Wiggins, M. Sandler

{"title":"A Method for Analysis of Shared Structure in Large Music Collections using Techniques from Genetic Sequencing and Graph Theory","authors":"F. Thalmann, Kazuyoshi Yoshii, Thomas Wilmering, Geraint A. Wiggins, M. Sandler","doi":"10.5281/ZENODO.4245440","DOIUrl":"https://doi.org/10.5281/ZENODO.4245440","url":null,"abstract":"While common approaches to automatic structural analysis of music typically focus on individual audio files, our approach collates audio features of large sets of related files in order to find a shared musical temporal structure. The content of each individual file and the differences between them can then be described in relation to this shared structure. We first construct a large similarity graph of temporal segments, such as beats or bars, based on self-alignments and selected pair-wise alignments between the given input files. Part of this graph is then partitioned into groups of corresponding segments using multiple sequence alignment. This partitioned graph is searched for recurring sections which can be organized hierarchically based on their co-occurrence. We apply our approach to discover shared harmonic structure in a dataset containing a large number of different live performances of a number of songs. Our evaluation shows that using the joint information from a number of files has the advantage of evening out the noisiness or inaccuracy of the underlying feature data and leads to a robust estimate of shared musical material.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127663662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joyful for you and tender for us: the influence of individual characteristics and language on emotion labeling and classification 你快乐，我们温柔:个体特征和语言对情绪标签和分类的影响

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245568

Juan Sebastián Gómez Cañón, Estefanía Cano, P. Herrera, E. Gómez

{"title":"Joyful for you and tender for us: the influence of individual characteristics and language on emotion labeling and classification","authors":"Juan Sebastián Gómez Cañón, Estefanía Cano, P. Herrera, E. Gómez","doi":"10.5281/ZENODO.4245568","DOIUrl":"https://doi.org/10.5281/ZENODO.4245568","url":null,"abstract":"Tagging a musical excerpt with an emotion label may result in a vague and ambivalent exercise. This subjectivity entangles several high-level music description tasks when the computational models built to address them produce predictions on the basis of a \"ground truth\". In this study, we investigate the relationship between emotions perceived in pop and rock music (mainly in Euro-American styles) and personal characteristics from the listener, using language as a key feature. Our goal is to understand the influence of lyrics comprehension on music emotion perception and use this knowledge to improve Music Emotion Recognition (MER) models. We systematically analyze over 30K annotations of 22 musical fragments to assess the impact of individual differences on agreement, as defined by Krippendorff's coefficient. We employ personal characteristics to form group-based annotations by assembling ratings with respect to listeners' familiarity, preference, lyrics comprehension, and music sophistication. Finally, we study our group-based annotations in a two-fold approach: (1) assessing the similarity within annotations using manifold learning algorithms and unsupervised clustering, and (2) analyzing their performance by training classification models with diverse \"ground truths\". Our results suggest that a) applying a broader categorization of taxonomies and b) using multi-label, group-based annotations based on language, can be beneficial for MER models.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126113213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Modeling Music and Code Knowledge to Support a Co-creative AI Agent for Education 为音乐和代码知识建模以支持共同创造的教育AI代理

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245386

J. Smith, E. Truesdell, Jason Freeman, Brian Magerko, K. Boyer, Tom McKlin

{"title":"Modeling Music and Code Knowledge to Support a Co-creative AI Agent for Education","authors":"J. Smith, E. Truesdell, Jason Freeman, Brian Magerko, K. Boyer, Tom McKlin","doi":"10.5281/ZENODO.4245386","DOIUrl":"https://doi.org/10.5281/ZENODO.4245386","url":null,"abstract":"EarSketch is an online environment for learning intro-ductory computing concepts through code-driven, sample-based music production. This paper details the design and implementation of a module to perform code and music analyses on projects on the EarSketch platform. This analysis module combines inputs in the form of symbolic metadata, audio feature analysis, and user code to produce com-prehensive models of user projects. The module performs a detailed analysis of the abstract syntax tree of a user’s code to model use of computational concepts. It uses music information retrieval (MIR) and symbolic metadata to analyze users’ musical design choices. These analyses produce a model containing users’ coding and musical deci-sions, as well as qualities of the algorithmic music created by those decisions. The models produced by this module will support future development of CAI, a Co-creative Artiﬁcial Intelligence. CAI is designed to collaborate with learners and promote increased competency and engagement with topics in the EarSketch curriculum. Our module combines code analysis and MIR to further the educational goals of CAI and EarSketch and to explore the application of multimodal analysis tools to education.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129921562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Less is more: Faster and better music version identification with embedding distillation 少即是多:更快，更好的音乐版本识别嵌入蒸馏

International Society for Music Information Retrieval Conference Pub Date : 2020-10-07 DOI: 10.5281/ZENODO.4245570

Furkan Yesiler, J. Serrà, E. Gómez

引用次数: 7

Polyphonic Piano Transcription Using Autoregressive Multi-State Note Model 基于自回归多态音符模型的钢琴复调转写

International Society for Music Information Retrieval Conference Pub Date : 2020-10-02 DOI: 10.5281/ZENODO.4245466

Taegyun Kwon, Dasaem Jeong, Juhan Nam

{"title":"Polyphonic Piano Transcription Using Autoregressive Multi-State Note Model","authors":"Taegyun Kwon, Dasaem Jeong, Juhan Nam","doi":"10.5281/ZENODO.4245466","DOIUrl":"https://doi.org/10.5281/ZENODO.4245466","url":null,"abstract":"Recent advances in polyphonic piano transcription have been made primarily by a deliberate design of neural network architectures that detect different note states such as onset or sustain and model the temporal evolution of the states. The majority of them, however, use separate neural networks for each note state, thereby optimizing multiple loss functions, and also they handle the temporal evolution of note states by abstract connections between the state-wise neural networks or using a post-processing module. In this paper, we propose a unified neural network architecture where multiple note states are predicted as a softmax output with a single loss function and the temporal order is learned by an auto-regressive connection within the single neural network. This compact model allows to increase note states without architectural complexity. Using the MAESTRO dataset, we examine various combinations of multiple note states including on, onset, sustain, re-onset, offset, and off. We also show that the autoregressive module effectively learns inter-state dependency of notes. Finally, we show that our proposed model achieves performance comparable to state-of-the-arts with fewer parameters.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116289001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction MIDI退化工具包:符号音乐增强和校正

International Society for Music Information Retrieval Conference Pub Date : 2020-09-30 DOI: 10.5281/ZENODO.4245566

Andrew Mcleod, James Owers, Kazuyoshi Yoshii

{"title":"The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction","authors":"Andrew Mcleod, James Owers, Kazuyoshi Yoshii","doi":"10.5281/ZENODO.4245566","DOIUrl":"https://doi.org/10.5281/ZENODO.4245566","url":null,"abstract":"In this paper, we introduce the MIDI Degradation Toolkit (MDTK), containing functions which take as input a musical excerpt (a set of notes with pitch, onset time, and duration), and return a \"degraded\" version of that excerpt with some error (or errors) introduced. Using the toolkit, we create the Altered and Corrupted MIDI Excerpts dataset version 1.0 (ACME v1.0), and propose four tasks of increasing difficulty to detect, classify, locate, and correct the degradations. We hypothesize that models trained for these tasks can be useful in (for example) improving automatic music transcription performance if applied as a post-processing step. To that end, MDTK includes a script that measures the distribution of different types of errors in a transcription, and creates a degraded dataset with similar properties. MDTK's degradations can also be applied dynamically to a dataset during training (with or without the above script), generating novel degraded excerpts each epoch. MDTK could also be used to test the robustness of any system designed to take MIDI (or similar) data as input (e.g. systems designed for voice separation, metrical alignment, or chord detection) to such transcription errors or otherwise noisy data. The toolkit and dataset are both publicly available online, and we encourage contribution and feedback from the community.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114726662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1