International Society for Music Information Retrieval Conference最新文献_第3页

Playing Technique Detection by Fusing Note Onset Information in Guzheng Performance 融合音符起始信息的古筝演奏技术检测

International Society for Music Information Retrieval Conference Pub Date : 2022-09-19 DOI: 10.48550/arXiv.2209.08774

Dichucheng Li, Yulun Wu, Qinyu Li, Jiahao Zhao, Yi Yu, F. Xia, Wei Li

{"title":"Playing Technique Detection by Fusing Note Onset Information in Guzheng Performance","authors":"Dichucheng Li, Yulun Wu, Qinyu Li, Jiahao Zhao, Yi Yu, F. Xia, Wei Li","doi":"10.48550/arXiv.2209.08774","DOIUrl":"https://doi.org/10.48550/arXiv.2209.08774","url":null,"abstract":"The Guzheng is a kind of traditional Chinese instruments with diverse playing techniques. Instrument playing techniques (IPT) play an important role in musical performance. However, most of the existing works for IPT detection show low efficiency for variable-length audio and provide no assurance in the generalization as they rely on a single sound bank for training and testing. In this study, we propose an end-to-end Guzheng playing technique detection system using Fully Convolutional Networks that can be applied to variable-length audio. Because each Guzheng playing technique is applied to a note, a dedicated onset detector is trained to divide an audio into several notes and its predictions are fused with frame-wise IPT predictions. During fusion, we add the IPT predictions frame by frame inside each note and get the IPT with the highest probability within each note as the final output of that note. We create a new dataset named GZ_IsoTech from multiple sound banks and real-world recordings for Guzheng performance analysis. Our approach achieves 87.97% in frame-level accuracy and 80.76% in note-level F1-score, outperforming existing works by a large margin, which indicates the effectiveness of our proposed method in IPT detection.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123583170","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: 3

Domain Adversarial Training on Conditional Variational Auto-Encoder for Controllable Music Generation 面向可控音乐生成的条件变分自编码器领域对抗训练

International Society for Music Information Retrieval Conference Pub Date : 2022-09-15 DOI: 10.48550/arXiv.2209.07144

Jingwei Zhao, Gus G. Xia, Ye Wang

{"title":"Domain Adversarial Training on Conditional Variational Auto-Encoder for Controllable Music Generation","authors":"Jingwei Zhao, Gus G. Xia, Ye Wang","doi":"10.48550/arXiv.2209.07144","DOIUrl":"https://doi.org/10.48550/arXiv.2209.07144","url":null,"abstract":"The variational auto-encoder has become a leading framework for symbolic music generation, and a popular research direction is to study how to effectively control the generation process. A straightforward way is to control a model using different conditions during inference. However, in music practice, conditions are usually sequential (rather than simple categorical labels), involving rich information that overlaps with the learned representation. Consequently, the decoder gets confused about whether to\"listen to\"the latent representation or the condition, and sometimes just ignores the condition. To solve this problem, we leverage domain adversarial training to disentangle the representation from condition cues for better control. Specifically, we propose a condition corruption objective that uses the representation to denoise a corrupted condition. Minimized by a discriminator and maximized by the VAE encoder, this objective adversarially induces a condition-invariant representation. In this paper, we focus on the task of melody harmonization to illustrate our idea, while our methodology can be generalized to other controllable generative tasks. Demos and experiments show that our methodology facilitates not only condition-invariant representation learning but also higher-quality controllability compared to baselines.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128895828","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

Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention 节拍变压器:与扩张的自我注意去混合拍和重拍跟踪

International Society for Music Information Retrieval Conference Pub Date : 2022-09-15 DOI: 10.48550/arXiv.2209.07140

Jingwei Zhao, Gus G. Xia, Ye Wang

引用次数: 7

Checklist Models for Improved Output Fluency in Piano Fingering Prediction 检查表模型提高输出流畅性在钢琴指法预测

International Society for Music Information Retrieval Conference Pub Date : 2022-09-12 DOI: 10.48550/arXiv.2209.05622

Nikita Srivatsan, Taylor Berg-Kirkpatrick

{"title":"Checklist Models for Improved Output Fluency in Piano Fingering Prediction","authors":"Nikita Srivatsan, Taylor Berg-Kirkpatrick","doi":"10.48550/arXiv.2209.05622","DOIUrl":"https://doi.org/10.48550/arXiv.2209.05622","url":null,"abstract":"In this work we present a new approach for the task of predicting fingerings for piano music. While prior neural approaches have often treated this as a sequence tagging problem with independent predictions, we put forward a checklist system, trained via reinforcement learning, that maintains a representation of recent predictions in addition to a hidden state, allowing it to learn soft constraints on output structure. We also demonstrate that by modifying input representations -- which in prior work using neural models have often taken the form of one-hot encodings over individual keys on the piano -- to encode relative position on the keyboard to the prior note instead, we can achieve much better performance. Additionally, we reassess the use of raw per-note labeling precision as an evaluation metric, noting that it does not adequately measure the fluency, i.e. human playability, of a model's output. To this end, we compare methods across several statistics which track the frequency of adjacent finger predictions that while independently reasonable would be physically challenging to perform in sequence, and implement a reinforcement learning strategy to minimize these as part of our training loss. Finally through human expert evaluation, we demonstrate significant gains in performability directly attributable to improvements with respect to these metrics.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"938 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123066195","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

Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments 利用采样乐器合成数据改善合唱音乐分离

International Society for Music Information Retrieval Conference Pub Date : 2022-09-07 DOI: 10.48550/arXiv.2209.02871

K. Chen, Hao-Wen Dong, Yi Luo, Julian McAuley, Taylor Berg-Kirkpatrick, M. Puckette, S. Dubnov

{"title":"Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments","authors":"K. Chen, Hao-Wen Dong, Yi Luo, Julian McAuley, Taylor Berg-Kirkpatrick, M. Puckette, S. Dubnov","doi":"10.48550/arXiv.2209.02871","DOIUrl":"https://doi.org/10.48550/arXiv.2209.02871","url":null,"abstract":"Choral music separation refers to the task of extracting tracks of voice parts (e.g., soprano, alto, tenor, and bass) from mixed audio. The lack of datasets has impeded research on this topic as previous work has only been able to train and evaluate models on a few minutes of choral music data due to copyright issues and dataset collection difficulties. In this paper, we investigate the use of synthesized training data for the source separation task on real choral music. We make three contributions: first, we provide an automated pipeline for synthesizing choral music data from sampled instrument plugins within controllable options for instrument expressiveness. This produces an 8.2-hour-long choral music dataset from the JSB Chorales Dataset and one can easily synthesize additional data. Second, we conduct an experiment to evaluate multiple separation models on available choral music separation datasets from previous work. To the best of our knowledge, this is the first experiment to comprehensively evaluate choral music separation. Third, experiments demonstrate that the synthesized choral data is of sufficient quality to improve the model's performance on real choral music datasets. This provides additional experimental statistics and data support for the choral music separation study.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126279041","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: 3

Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation 在音频域环路生成中利用预训练特征网络生成对抗网络

International Society for Music Information Retrieval Conference Pub Date : 2022-09-05 DOI: 10.48550/arXiv.2209.01751

Yen-Tung Yeh, Bo-Yu Chen, Yi-Hsuan Yang

{"title":"Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation","authors":"Yen-Tung Yeh, Bo-Yu Chen, Yi-Hsuan Yang","doi":"10.48550/arXiv.2209.01751","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01751","url":null,"abstract":"While generative adversarial networks (GANs) have been widely used in research on audio generation, the training of a GAN model is known to be unstable, time consuming, and data inefficient. Among the attempts to ameliorate the training process of GANs, the idea of Projected GAN emerges as an effective solution for GAN-based image generation, establishing the state-of-the-art in different image applications. The core idea is to use a pre-trained classifier to constrain the feature space of the discriminator to stabilize and improve GAN training. This paper investigates whether Projected GAN can similarly improve audio generation, by evaluating the performance of a StyleGAN2-based audio-domain loop generation model with and without using a pre-trained feature space in the discriminator. Moreover, we compare the performance of using a general versus domain-specific classifier as the pre-trained audio classifier. With experiments on both drum loop and synth loop generation, we show that a general audio classifier works better, and that with Projected GAN our loop generation models can converge around 5 times faster without performance degradation.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121240164","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

Equivariant Self-Supervision for Musical Tempo Estimation 音乐速度估计的等变自监督

International Society for Music Information Retrieval Conference Pub Date : 2022-09-03 DOI: 10.48550/arXiv.2209.01478

Elio Quinton

{"title":"Equivariant Self-Supervision for Musical Tempo Estimation","authors":"Elio Quinton","doi":"10.48550/arXiv.2209.01478","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01478","url":null,"abstract":"Self-supervised methods have emerged as a promising avenue for representation learning in the recent years since they alleviate the need for labeled datasets, which are scarce and expensive to acquire. Contrastive methods are a popular choice for self-supervision in the audio domain, and typically provide a learning signal by forcing the model to be invariant to some transformations of the input. These methods, however, require measures such as negative sampling or some form of regularisation to be taken to prevent the model from collapsing on trivial solutions. In this work, instead of invariance, we propose to use equivariance as a self-supervision signal to learn audio tempo representations from unlabelled data. We derive a simple loss function that prevents the network from collapsing on a trivial solution during training, without requiring any form of regularisation or negative sampling. Our experiments show that it is possible to learn meaningful representations for tempo estimation by solely relying on equivariant self-supervision, achieving performance comparable with supervised methods on several benchmarks. As an added benefit, our method only requires moderate compute resources and therefore remains accessible to a wide research community.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129740988","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: 4

"More Than Words": Linking Music Preferences and Moral Values Through Lyrics “超越文字”:通过歌词连接音乐偏好和道德价值观

International Society for Music Information Retrieval Conference Pub Date : 2022-09-02 DOI: 10.48550/arXiv.2209.01169

Vjosa Preniqi, Kyriaki Kalimeri, C. Saitis

{"title":"\"More Than Words\": Linking Music Preferences and Moral Values Through Lyrics","authors":"Vjosa Preniqi, Kyriaki Kalimeri, C. Saitis","doi":"10.48550/arXiv.2209.01169","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01169","url":null,"abstract":"This study explores the association between music preferences and moral values by applying text analysis techniques to lyrics. Harvesting data from a Facebook-hosted application, we align psychometric scores of 1,386 users to lyrics from the top 5 songs of their preferred music artists as emerged from Facebook Page Likes. We extract a set of lyrical features related to each song's overarching narrative, moral valence, sentiment, and emotion. A machine learning framework was designed to exploit regression approaches and evaluate the predictive power of lyrical features for inferring moral values. Results suggest that lyrics from top songs of artists people like inform their morality. Virtues of hierarchy and tradition achieve higher prediction scores ($.20 leq r leq .30$) than values of empathy and equality ($.08 leq r leq .11$), while basic demographic variables only account for a small part in the models' explainability. This shows the importance of music listening behaviours, as assessed via lyrical preferences, alone in capturing moral values. We discuss the technological and musicological implications and possible future improvements.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122976020","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

AccoMontage2: A Complete Harmonization and Accompaniment Arrangement System 配套2:一个完整的和声与伴奏安排体系

International Society for Music Information Retrieval Conference Pub Date : 2022-09-01 DOI: 10.48550/arXiv.2209.00353

Li Yi, Haochen Hu, Jingwei Zhao, Gus G. Xia

{"title":"AccoMontage2: A Complete Harmonization and Accompaniment Arrangement System","authors":"Li Yi, Haochen Hu, Jingwei Zhao, Gus G. Xia","doi":"10.48550/arXiv.2209.00353","DOIUrl":"https://doi.org/10.48550/arXiv.2209.00353","url":null,"abstract":"We propose AccoMontage2, a system capable of doing full-length song harmonization and accompaniment arrangement based on a lead melody. Following AccoMontage, this study focuses on generating piano arrangements for popular/folk songs and it carries on the generalized template-based retrieval method. The novelties of this study are twofold. First, we invent a harmonization module (which AccoMontage does not have). This module generates structured and coherent full-length chord progression by optimizing and balancing three loss terms: a micro-level loss for note-wise dissonance, a meso-level loss for phrase-template matching, and a macro-level loss for full piece coherency. Second, we develop a graphical user interface which allows users to select different styles of chord progression and piano texture. Currently, chord progression styles include Pop, R&B, and Dark, while piano texture styles include several levels of voicing density and rhythmic complexity. Experimental results show that both our harmonization and arrangement results significantly outperform the baselines. Lastly, we release AccoMontage2 as an online application as well as the organized chord progression templates as a public dataset.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126667241","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

What is missing in deep music generation? A study of repetition and structure in popular music 深度音乐的产生缺少了什么?对流行音乐中重复和结构的研究

International Society for Music Information Retrieval Conference Pub Date : 2022-09-01 DOI: 10.48550/arXiv.2209.00182

Shuqi Dai, Huiran Yu, R. Dannenberg

{"title":"What is missing in deep music generation? A study of repetition and structure in popular music","authors":"Shuqi Dai, Huiran Yu, R. Dannenberg","doi":"10.48550/arXiv.2209.00182","DOIUrl":"https://doi.org/10.48550/arXiv.2209.00182","url":null,"abstract":"Structure is one of the most essential aspects of music, and music structure is commonly indicated through repetition. However, the nature of repetition and structure in music is still not well understood, especially in the context of music generation, and much remains to be explored with Music Information Retrieval (MIR) techniques. Analyses of two popular music datasets (Chinese and American) illustrate important music construction principles: (1) structure exists at multiple hierarchical levels, (2) songs use repetition and limited vocabulary so that individual songs do not follow general statistics of song collections, (3) structure interacts with rhythm, melody, harmony, and predictability, and (4) over the course of a song, repetition is not random, but follows a general trend as revealed by cross-entropy. These and other findings offer challenges as well as opportunities for deep-learning music generation and suggest new formal music criteria and evaluation methods. Music from recent music generation systems is analyzed and compared to human-composed music in our datasets, often revealing striking differences from a structural perspective.","PeriodicalId":309903,"journal":{"name":"International Society for Music Information Retrieval Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116845109","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: 8