International Society for Music Information Retrieval Conference最新文献_第8页

Mode classification and natural units in plainchant 平调中的模式分类与自然单位

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245572

B. Cornelissen, W. Zuidema, J. Burgoyne

{"title":"Mode classification and natural units in plainchant","authors":"B. Cornelissen, W. Zuidema, J. Burgoyne","doi":"10.5281/ZENODO.4245572","DOIUrl":"https://doi.org/10.5281/ZENODO.4245572","url":null,"abstract":"Many musics across the world are structured around multiple modes, which hold a middle ground between scales and melodies. We study whether we can classify mode in a corpus of 20,865 medieval plainchant melodies from the Cantus database. We revisit the traditional ‘textbook’ classification approach (using the final, the range and initial note) as well as the only prior computational study we are aware of, which uses pitch profiles. Both approaches work well, but largely reduce modes to scales and ignore their melodic character. Our main contribution is a model that reaches 93–95% F1 score on mode classification, compared to 86– 90% using traditional pitch-based musicological methods. Importantly, it reaches 81–83% even when we discard all absolute pitch information and reduce a melody to its contour. The model uses tf–idf vectors and strongly depends on the choice of units: i.e., how the melody is segmented. If we borrow the syllable or word structure from the lyrics, the model outperforms all of our baselines. This suggests that, like language, music is made up of ‘natural’ units, in our case between the level of notes and complete phrases, a finding that may well be useful in other musics.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"33 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":"121629153","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: 5

From Music Ontology towards Ethno-Music-Ontology 从音乐本体到民族音乐本体

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245586

Polina Proutskova, A. Volk, Peyman Heydarian, György Fazekas

引用次数: 2

Programming Inequality: Gender Representation on Canadian Country Radio (2005-2019) 节目不平等:加拿大乡村广播电台的性别代表性(2005-2019)

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245452

J. Watson

{"title":"Programming Inequality: Gender Representation on Canadian Country Radio (2005-2019)","authors":"J. Watson","doi":"10.5281/ZENODO.4245452","DOIUrl":"https://doi.org/10.5281/ZENODO.4245452","url":null,"abstract":"In May 2015, a consultant for country radio revealed a decades’ long practice of limiting space for songs by female artists. He encouraged program directors to avoid playing songs by women back-to-back and advocated for programming their songs at 13-15% of station playlists. His words sparked debate within the industry and drew attention to growing inequalities on radio and within the genre. The majority of these discussions have centered on US country radio, with limited attention to the growing imbalance on the format in Canada. While country format radio in both countries subscribe to a practice of gender-based programming, Canadian program directors are governed by the federal Broadcasting Act, which regulates dissemination of Canadian content. Using metadata extracted from one of the main radio monitoring services – Mediabase, this paper examines gender-related trends on Canadian country format radio between 2005 and 2019. Through data-driven analysis of Mediabase’s weekly re-ports, this paper shows declining representation of songs by women on Canadian country radio and addresses the impact of Canadian content regulations on this process.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"78 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":"123886422","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: 5

Towards a Formalization of Musical Rhythm 走向音乐节奏的形式化

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245508

M. Rohrmeier

引用次数: 14

Automatic Rank-Ordering of Singing Vocals with Twin-Neural Network 基于双神经网络的声乐自动排序

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245458

Chitralekha Gupta, Lin Huang, Haizhou Li

{"title":"Automatic Rank-Ordering of Singing Vocals with Twin-Neural Network","authors":"Chitralekha Gupta, Lin Huang, Haizhou Li","doi":"10.5281/ZENODO.4245458","DOIUrl":"https://doi.org/10.5281/ZENODO.4245458","url":null,"abstract":"When making judgements, humans are known to be better at choosing a preferred option amongst a small number of options, rather than giving an absolute ranking of all the options. This preference-based judgment rank-ordering method is called Best-Worst Scaling (BWS). Inspired by this concept, we propose a preference-based framework to generate a relative rank-ordering of singing vocals, and therefore, singers. We adopt a twin-neural network (Siamese) that learns to choose a preferred candidate in terms of singing quality between two inputs. With a few such pairwise comparisons, this method generates a relative rank-order of a complete list of singers. Additionally, we incorporate a knowledge-based musically-relevant pitch histogram representation, as a conditioning vector, to provide explicit musical information to the network. The experiments show that this method is able to reliably evaluate singing quality and rank-order singing vocals, independent of the song or the singer. The results suggest that the twin-neural network learns the underlying discerning properties relevant to singing quality, instead of being specific to the content of a song or singer.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"37 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":"117076525","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

Attributes-Aware Deep Music Transformation 感知属性的深度音乐转换

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245520

Lisa Kawai, P. Esling, Tatsuya Harada

{"title":"Attributes-Aware Deep Music Transformation","authors":"Lisa Kawai, P. Esling, Tatsuya Harada","doi":"10.5281/ZENODO.4245520","DOIUrl":"https://doi.org/10.5281/ZENODO.4245520","url":null,"abstract":"Recent machine learning techniques have enabled a large variety of novel music generation processes. However, most approaches do not provide any form of interpretable control over musical attributes, such as pitch and rhythm. Obtaining control over the generation process is critically important for its use in real-life creative setups. Nevertheless, this problem remains arduous, as there are no known functions nor differentiable approximations to transform symbolic music with control of musical attributes.In this work, we propose a novel method that enables attributes-aware music transformation from any set of musical annotations, without requiring complicated derivative implementation. By relying on an adversarial confusion criterion on given musical annotations, we force the latent space of a generative model to abstract from these features. Then, reintroducing these features as conditioning to the generative function, we obtain a continuous control over them. To demonstrate our approach, we rely on sets of musical attributes computed by the jSymbolic library as annotations and conduct experiments that show that our method outperforms previous methods in control. Finally, comparing correlations between attributes and the transformed results show that our method can provide explicit control over any continuous or discrete annotation.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"104 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":"122551487","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: 13

Score-Informed Source Separation of Choral Music 基于乐谱的合唱音乐源分离

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245412

M. Gover, P. Depalle

{"title":"Score-Informed Source Separation of Choral Music","authors":"M. Gover, P. Depalle","doi":"10.5281/ZENODO.4245412","DOIUrl":"https://doi.org/10.5281/ZENODO.4245412","url":null,"abstract":"Choral music recordings are a particularly challenging target for source separation due to the choral blend and the inherent acoustical complexity of the ‘choral timbre’. Due to the scarcity of publicly available multi-track choir recordings, we create a dataset of synthesized Bach chorales. We apply data augmentation to alter the chorales so that they more faithfully represent music from a broader range of choral genres. For separation we employ Wave-U-Net, a time-domain convolutional neural network (CNN) originally proposed for vocals and accompaniment separation. We show that Wave-U-Net outperforms a baseline implemented using score-informed NMF (non-negative matrix factorization). We introduce score-informed Wave-U-Net to incorporate the musical score into the separation process. We experiment with different score conditioning methods and show that conditioning on the score leads to improved separation results. We propose a ‘score-guided’ model variant in which separation is guided by the score alone, bypassing the need to specify the identity of the extracted source. Finally, we evaluate our models (trained on synthetic data only) on real choir recordings and find that in the absence of a large training set of real recordings, NMF still performs better than Wave-U-Net in this setting. To our knowledge, this paper is the first to study source separation of choral music.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"80 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":"123256737","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: 17

Play Music: User Motivations and Expectations for Non-Specific Voice Queries 播放音乐:用户对非特定语音查询的动机和期望

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245524

Jennifer Thom-Santelli, Angela Nazarian, R. Brillman, H. Cramer, Sarah Mennicken

{"title":"Play Music: User Motivations and Expectations for Non-Specific Voice Queries","authors":"Jennifer Thom-Santelli, Angela Nazarian, R. Brillman, H. Cramer, Sarah Mennicken","doi":"10.5281/ZENODO.4245524","DOIUrl":"https://doi.org/10.5281/ZENODO.4245524","url":null,"abstract":"The growing market of voice-enabled devices introduces new types of music search requests that can be more ambiguous than in typed search interfaces as voice assistants can potentially support conversational requests. However, these systems may not be able to fulfill ambiguous requests in a manner that matches the user need. In this work, we study an example of ambiguous requests which we term as non-specific queries (NSQs), such as \"play music,\" where users ask to stream content using a single utterance that does not specify what content they want to hear. To better understand user motivations for making NSQs, we conducted semi-structured qualitative interviews with voice users. We observed four themes that structure user perceptions of the benefits and shortcomings of making NSQs: the tradeoff between control and convenience, varying expectations for personalization, the effects of context on expectations, and learned user behaviors. We conclude with implications for how these themes can inform the interaction design of voice search systems in handling non-specific music requests in voice search systems.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"14 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":"128791439","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

The Rhythmic Dictator: Does Gamification of Rhythm Dictation Exercises Help? 节奏独裁者:游戏化的节奏听写练习有帮助吗?

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245478

Matevž Pesek, Lovro Suhadolnik, Peter Šavli, M. Marolt

引用次数: 2

User Insights on Diversity in Music Recommendation Lists 用户对音乐推荐列表多样性的见解

International Society for Music Information Retrieval Conference Pub Date : 2020-10-11 DOI: 10.5281/ZENODO.4245464

Kyle Robinson, Dan Brown, M. Schedl

{"title":"User Insights on Diversity in Music Recommendation Lists","authors":"Kyle Robinson, Dan Brown, M. Schedl","doi":"10.5281/ZENODO.4245464","DOIUrl":"https://doi.org/10.5281/ZENODO.4245464","url":null,"abstract":"While many researchers have proposed various ways of quantifying recommendation list diversity, these approaches have had little input from users on their own perceptions and preferences in seeking diversity. Through an exploratory user study, we provide a better understanding of how users view the concept of diversity in music recommendations, and how they might optimise levels of intra-list diversity themselves. In our study, 17 participants interacted with and rated the suggestions from two different recommendation systems. One provided static top-7 collaborative filtering recommendations, and the other provided an interactive slider to re-rank these recommendations based on a continuous diversity scale. We also asked participants a series of free-form questions on music discovery and diversity in semi-structured interviews. User-preferred levels of diversity varied widely both within and between subjects. Although most users agreed that diversity is beneficial in music discovery, they also noted a risk of dissatisfaction from too much diversity. A key finding is that preference for diversification was often linked to user mood. Participants also expressed a clear distinction between diversity within existing preferences, and outside of existing preferences. These ideas of inner and outer diversity are not well defined within the bounds of current diversity metrics, and we discuss their implications.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"20 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":"122457273","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: 6