今日论文合集：cs.SD语音5篇，eess.AS音频处理7篇。
cs.SD语音
【1】 From West to East: Who can understand the music of the others better?标题：从西方到东方：谁能更好地理解别人的音乐？链接：https://arxiv.org/abs/2307.09795
作者：Charilaos Papaioannou,Emmanouil Benetos,Alexandros Potamianos机构：School of ECE, National Technical University of Athens, Greece,  Centre for Digital Music, Queen Mary University of London, UK摘要：MIR的最新发展导致了几个基准深度学习模型，其嵌入可用于各种下游任务。同时，这些模型中的绝大多数都接受过西方流行/摇滚音乐和相关风格的训练。这就引出了一个研究问题，即这些模型是否可以用于学习不同音乐文化和风格的表示，或者我们是否可以构建类似的音乐音频嵌入模型，这些模型是在来自不同文化或风格的数据上训练的。为此，我们利用迁移学习方法来了解数据所属的不同音乐文化之间的相似性。我们使用两个西方音乐数据集，两个传统/民间数据集来自东地中海文化，两个数据集属于印度艺术音乐。三个深度音频嵌入模型被训练并跨域传输，包括两个基于CNN的架构和一个基于Transformer的架构，以对每个目标域数据集执行自动标记。实验结果表明，通过迁移学习，在所有领域都实现了有竞争力的性能，而最佳源数据集因音乐文化而异。实现和训练的模型都在公共存储库中提供。摘要：Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music and related styles. This leads to research questions on whether these models can be used to learn representations for different music cultures and styles, or whether we can build similar music audio embedding models trained on data from different cultures or styles. To that end, we leverage transfer learning methods to derive insights about the similarities between the different music cultures to which the data belongs to. We use two Western music datasets, two traditional/folk datasets coming from eastern Mediterranean cultures, and two datasets belonging to Indian art music. Three deep audio embedding models are trained and transferred across domains, including two CNN-based and a Transformer-based architecture, to perform auto-tagging for each target domain dataset. Experimental results show that competitive performance is achieved in all domains via transfer learning, while the best source dataset varies for each music culture. The implementation and the trained models are both provided in a public repository.
【2】 DisCover: Disentangled Music Representation Learning for Cover Song  Identification标题：DISCOVER：用于翻唱歌曲识别的解缠音乐表征学习链接：https://arxiv.org/abs/2307.09775
作者：Jiahao Xun,Shengyu Zhang,Yanting Yang,Jieming Zhu,Liqun Deng,Zhou Zhao,Zhenhua Dong,Ruiqi Li,Lichao Zhang,Fei Wu机构：Zhejiang University, Hangzhou, China, Huawei Noah’s Ark Lab, Shenzhen, China摘要：在音乐信息检索（MIR）领域，翻唱歌曲识别（CSI）是一项具有挑战性的任务，其目的是从海量的音乐收藏中识别出查询歌曲的翻唱版本。现有的作品仍然遭受高的歌曲内方差和歌曲间的相关性，由于纠缠的性质的特定版本和版本不变的因素在他们的建模。在这项工作中，我们设定的目标是解开特定版本和版本不变的因素，这可以使模型更容易地学习未知查询歌曲的不变的音乐表示。我们分析CSI任务在解纠缠的角度与因果图技术，并确定内部版本和内部版本的影响偏置不变学习。为了阻止这些影响，我们提出了解开音乐表征学习框架（Discover）CSI。Discoverer由两个关键组件组成：（1）知识引导的解纠缠模块（KDM）和（2）基于梯度的对抗解纠缠模块（GADM），其分别阻止版本内和版本间偏差效应。KDM最小化学习的表示和版本变化的因素之间的互信息，识别与先验的领域知识。GADM通过模拟歌曲内版本之间的表示转换来识别版本变化的因素，并利用对抗蒸馏的效果阻断。与性能最佳的方法进行了广泛的比较和深入的分析，证明了Discoverer的有效性和CSI解纠缠的必要性。摘要：In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collection. Existing works still suffer from high intra-song variances and inter-song correlations, due to the entangled nature of version-specific and version-invariant factors in their modeling. In this work, we set the goal of disentangling version-specific and version-invariant factors, which could make it easier for the model to learn invariant music representations for unseen query songs. We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning. To block these effects, we propose the disentangled music representation learning framework (DisCover) for CSI. DisCover consists of two critical components: (1) Knowledge-guided Disentanglement Module (KDM) and (2) Gradient-based Adversarial Disentanglement Module (GADM), which block intra-version and inter-version biased effects, respectively. KDM minimizes the mutual information between the learned representations and version-variant factors that are identified with prior domain knowledge. GADM identifies version-variant factors by simulating the representation transitions between intra-song versions, and exploits adversarial distillation for effect blocking. Extensive comparisons with best-performing methods and in-depth analysis demonstrate the effectiveness of DisCover and the and necessity of disentanglement for CSI.
【3】 Improving Domain Generalization for Sound Classification with Sparse  Frequency-Regularized Transformer标题：用稀疏频率正则化Transformer改进域泛化的声音分类链接：https://arxiv.org/abs/2307.09723
作者：Honglin Mu,Wentian Xia,Wanxiang Che机构：Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China备注：Accepted by ICME 2023摘要：声音分类模型的性能受到对分布外（OOD）数据的泛化的影响。已经提出了许多方法来帮助模型推广。然而，大多数算法要么引入推理开销，要么专注于持久的CNN变体，而Transformers已被证明在许多自然语言处理和计算机视觉任务中优于CNN。我们提出了FRITO，一种有效的正则化技术的Transformer的自我注意，以提高模型的泛化能力，通过限制每个序列位置的注意感受域沿频谱图的频率维度。实验表明，我们的方法可以帮助Transformer模型在TAU 2020和Nsynth数据集上实现SOTA泛化性能，同时节省20%的推理时间。摘要：Sound classification models' performance suffers from generalizing on out-of-distribution (OOD) data. Numerous methods have been proposed to help the model generalize. However, most either introduce inference overheads or focus on long-lasting CNN-variants, while Transformers has been proven to outperform CNNs on numerous natural language processing and computer vision tasks. We propose FRITO, an effective regularization technique on Transformer's self-attention, to improve the model's generalization ability by limiting each sequence position's attention receptive field along the frequency dimension on the spectrogram. Experiments show that our method helps Transformer models achieve SOTA generalization performance on TAU 2020 and Nsynth datasets while saving 20% inference time.
【4】 JAZZVAR: A Dataset of Variations found within Solo Piano Performances of  Jazz Standards for Music Overpainting标题：JAZZVAR：爵士乐音乐覆盖标准独奏钢琴演奏中的变奏数据集链接：https://arxiv.org/abs/2307.09670
作者：Eleanor Row,Jingjing Tang,George Fazekas机构：Centre for Digital Music, Queen Mary University of London备注：Pre-print accepted for publication at CMMR2023, 12 pages, 4 figures摘要：爵士钢琴家常常对爵士乐标准有独特的诠释。从这些解释的段落可以被看作是变异的部分。我们手动提取这样的变化从独奏爵士钢琴演奏。JAZZVAR数据集是502对Variation和Original MIDI片段的集合。数据集中的每个变奏都伴随着一个对应的原始片段，其中包含来自原始爵士乐标准的旋律和和弦。我们的方法不同于音乐信息检索（MIR）社区中的许多现有爵士乐数据集，这些数据集通常专注于爵士乐表演中的即兴部分。在本文中，我们概述了获得和排序曲目的策展过程，创建原始和变化对的管道，以及我们对数据集的分析。我们还介绍了一个新的生成音乐任务，音乐覆盖，并提出了一个基线Transformer模型训练的JAZZVAR数据集的这项任务。我们的数据集的其他潜在应用包括表达性能分析和表演者识别。摘要：Jazz pianists often uniquely interpret jazz standards. Passages from these interpretations can be viewed as sections of variation. We manually extracted such variations from solo jazz piano performances. The JAZZVAR dataset is a collection of 502 pairs of Variation and Original MIDI segments. Each Variation in the dataset is accompanied by a corresponding Original segment containing the melody and chords from the original jazz standard. Our approach differs from many existing jazz datasets in the music information retrieval (MIR) community, which often focus on improvisation sections within jazz performances. In this paper, we outline the curation process for obtaining and sorting the repertoire, the pipeline for creating the Original and Variation pairs, and our analysis of the dataset. We also introduce a new generative music task, Music Overpainting, and present a baseline Transformer model trained on the JAZZVAR dataset for this task. Other potential applications of our dataset include expressive performance analysis and performer identification.
【5】 Alzheimer's Disease Detection from Spontaneous Speech and Text: A review标题：基于自发语音和文本的阿尔茨海默病检测研究进展链接：https://arxiv.org/abs/2307.10005
作者：Vrindha M. K.,Geethu V.,Anurenjan P. R.,Deepak S.,Sreeni K. G.机构：†Computer Vision Lab, College of Engineering Trivandrum, Kerala., ‡Rajiv Gandhi Institute of Technology, Kottayam, Kerala., †‡Affiliated to APJ Abdul Kalam Technological University, Trivandrum, Kerala, India.摘要：在过去的十年中，有一个激增的研究检查使用的声音和语音分析作为一种手段，检测神经退行性疾病，如阿尔茨海默氏症。许多研究已经表明，某些声学特征可以用于区分正常衰老和阿尔茨海默病，并且已经发现语音分析是检测阿尔茨海默氏痴呆症的具有成本效益的方法。本文的目的是分析在基于语音的阿尔茨海默病的检测和分类中使用的各种算法。使用Web of Science、Google Scholar和Science Direct等数据库进行了文献调查，并根据“阿尔茨海默氏症检测”、“语音”和“自然语言处理”等关键词纳入了2020年1月至今发表的文章。“ADReSS，Pitt语料库和CCC数据集通常用于从语音中分析痴呆症，本文重点介绍了来自15项研究的各种基于声学和语言特征工程的分类模型。  根据这项研究的结果，它似乎可以开发一个更准确的模型来分类阿尔茨海默氏症，同时考虑语言和声学数据。该综述表明，语音信号可以是检测痴呆症的有用工具，并可能作为有效识别阿尔茨海默病的可靠生物标志物。摘要：In the past decade, there has been a surge in research examining the use of voice and speech analysis as a means of detecting neurodegenerative diseases such as Alzheimer's. Many studies have shown that certain acoustic features can be used to differentiate between normal aging and Alzheimer's disease, and speech analysis has been found to be a cost-effective method of detecting Alzheimer's dementia. The aim of this review is to analyze the various algorithms used in speech-based detection and classification of Alzheimer's disease. A literature survey was conducted using databases such as Web of Science, Google Scholar, and Science Direct, and articles published from January 2020 to the present were included based on keywords such as ``Alzheimer's detection'', "speech," and "natural language processing." The ADReSS, Pitt corpus, and CCC datasets are commonly used for the analysis of dementia from speech, and this review focuses on the various acoustic and linguistic feature engineering-based classification models drawn from 15 studies.  Based on the findings of this study, it appears that a more accurate model for classifying Alzheimer's disease can be developed by considering both linguistic and acoustic data. The review suggests that speech signals can be a useful tool for detecting dementia and may serve as a reliable biomarker for efficiently identifying Alzheimer's disease.
eess.AS音频处理
【1】 Alzheimer's Disease Detection from Spontaneous Speech and Text: A review标题：基于自发语音和文本的阿尔茨海默病检测研究进展链接：https://arxiv.org/abs/2307.10005
作者：Vrindha M. K.,Geethu V.,Anurenjan P. R.,Deepak S.,Sreeni K. G.机构：†Computer Vision Lab, College of Engineering Trivandrum, Kerala., ‡Rajiv Gandhi Institute of Technology, Kottayam, Kerala., †‡Affiliated to APJ Abdul Kalam Technological University, Trivandrum, Kerala, India.摘要：在过去的十年中，有一个激增的研究检查使用的声音和语音分析作为一种手段，检测神经退行性疾病，如阿尔茨海默氏症。许多研究已经表明，某些声学特征可以用于区分正常衰老和阿尔茨海默病，并且已经发现语音分析是检测阿尔茨海默氏痴呆症的具有成本效益的方法。本文的目的是分析在基于语音的阿尔茨海默病的检测和分类中使用的各种算法。使用Web of Science、Google Scholar和Science Direct等数据库进行了文献调查，并根据“阿尔茨海默氏症检测”、“语音”和“自然语言处理”等关键词纳入了2020年1月至今发表的文章。“ADReSS，Pitt语料库和CCC数据集通常用于从语音中分析痴呆症，本文重点介绍了来自15项研究的各种基于声学和语言特征工程的分类模型。  根据这项研究的结果，它似乎可以开发一个更准确的模型来分类阿尔茨海默氏症，同时考虑语言和声学数据。该综述表明，语音信号可以是检测痴呆症的有用工具，并可能作为有效识别阿尔茨海默病的可靠生物标志物。摘要：In the past decade, there has been a surge in research examining the use of voice and speech analysis as a means of detecting neurodegenerative diseases such as Alzheimer's. Many studies have shown that certain acoustic features can be used to differentiate between normal aging and Alzheimer's disease, and speech analysis has been found to be a cost-effective method of detecting Alzheimer's dementia. The aim of this review is to analyze the various algorithms used in speech-based detection and classification of Alzheimer's disease. A literature survey was conducted using databases such as Web of Science, Google Scholar, and Science Direct, and articles published from January 2020 to the present were included based on keywords such as ``Alzheimer's detection'', "speech," and "natural language processing." The ADReSS, Pitt corpus, and CCC datasets are commonly used for the analysis of dementia from speech, and this review focuses on the various acoustic and linguistic feature engineering-based classification models drawn from 15 studies.  Based on the findings of this study, it appears that a more accurate model for classifying Alzheimer's disease can be developed by considering both linguistic and acoustic data. The review suggests that speech signals can be a useful tool for detecting dementia and may serve as a reliable biomarker for efficiently identifying Alzheimer's disease.
【2】 An analysis on the effects of speaker embedding choice in non  auto-regressive TTS标题：非自回归TTS中说话人嵌入选择的影响分析链接：https://arxiv.org/abs/2307.09898
作者：Adriana Stan,Johannah O'Mahony机构：Communications Department, Technical University of Cluj-Napoca, Romania, Centre for Speech Technology Research, University of Edinburgh, United Kingdom备注：Accepted for publication at ISCA Speech Synthesis Workshop 2023摘要：在本文中，我们介绍了第一次尝试，了解如何非自回归因子化的多说话人语音合成架构利用信息存在于不同的说话人嵌入集。我们分析，如果联合学习的表示，并从预训练的模型初始化它们确定目标说话人身份的任何质量改进。在一个单独的分析中，我们研究了不同的嵌入集如何影响网络的核心语音抽象（即零条件）在说话者身份和表示学习方面。我们表明，无论使用的嵌入和学习策略集，网络可以处理各种说话者身份同样好，几乎没有明显的变化的语音输出质量，和发言人泄漏的核心结构的合成系统是不可避免的标准训练程序迄今为止采用。摘要：In this paper we introduce a first attempt on understanding how a non-autoregressive factorised multi-speaker speech synthesis architecture exploits the information present in different speaker embedding sets. We analyse if jointly learning the representations, and initialising them from pretrained models determine any quality improvements for target speaker identities. In a separate analysis, we investigate how the different sets of embeddings impact the network's core speech abstraction (i.e. zero conditioned) in terms of speaker identity and representation learning. We show that, regardless of the used set of embeddings and learning strategy, the network can handle various speaker identities equally well, with barely noticeable variations in speech output quality, and that speaker leakage within the core structure of the synthesis system is inevitable in the standard training procedures adopted thus far.
【3】 Self-Supervised Acoustic Word Embedding Learning via Correspondence  Transformer Encoder标题：基于对应变换编码器的自监督声学单词嵌入学习链接：https://arxiv.org/abs/2307.09871
作者：Jingru Lin,Xianghu Yue,Junyi Ao,Haizhou Li机构：Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong, Kong, Shenzhen, China摘要：声学词嵌入（AWE）的目的是将可变长度的语音段映射到固定维度的表示。高质量的AWE应该是不变的变化，如持续时间，音高和扬声器。在本文中，我们介绍了一种新的自监督的方法来学习强大的AWE从大规模的未标记的语音语料库。我们的模型，名为通信Transformer编码器（CTE），采用了教师-学生的学习框架。我们基于同一个单词的不同实现在底层嵌入空间中应该是接近的这一想法来训练模型。具体而言，我们向教师和学生编码器提供相同单词的不同声学实例，并预训练具有单词级损失的模型。我们的实验表明，从建议的CTE模型提取的嵌入是鲁棒的语音变化，例如。演讲者和领域。此外，当评估Xitsonga，一个低资源的跨语言设置，CTE模型实现了新的国家的最先进的性能。摘要：Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a novel self-supervised method to learn robust AWEs from a large-scale unlabelled speech corpus. Our model, named Correspondence Transformer Encoder (CTE), employs a teacher-student learning framework. We train the model based on the idea that different realisations of the same word should be close in the underlying embedding space. Specifically, we feed the teacher and student encoder with different acoustic instances of the same word and pre-train the model with a word-level loss. Our experiments show that the embeddings extracted from the proposed CTE model are robust to speech variations, e.g. speakers and domains. Additionally, when evaluated on Xitsonga, a low-resource cross-lingual setting, the CTE model achieves new state-of-the-art performance.
【4】 From West to East: Who can understand the music of the others better?标题：从西方到东方：谁能更好地理解别人的音乐？链接：https://arxiv.org/abs/2307.09795
作者：Charilaos Papaioannou,Emmanouil Benetos,Alexandros Potamianos机构：School of ECE, National Technical University of Athens, Greece,  Centre for Digital Music, Queen Mary University of London, UK摘要：MIR的最新发展导致了几个基准深度学习模型，其嵌入可用于各种下游任务。同时，这些模型中的绝大多数都接受过西方流行/摇滚音乐和相关风格的训练。这就引出了一个研究问题，即这些模型是否可以用于学习不同音乐文化和风格的表示，或者我们是否可以构建类似的音乐音频嵌入模型，这些模型是在来自不同文化或风格的数据上训练的。为此，我们利用迁移学习方法来了解数据所属的不同音乐文化之间的相似性。我们使用两个西方音乐数据集，两个传统/民间数据集来自东地中海文化，两个数据集属于印度艺术音乐。三个深度音频嵌入模型被训练并跨域传输，包括两个基于CNN的架构和一个基于Transformer的架构，以对每个目标域数据集执行自动标记。实验结果表明，通过迁移学习，在所有领域都实现了有竞争力的性能，而最佳源数据集因音乐文化而异。实现和训练的模型都在公共存储库中提供。摘要：Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music and related styles. This leads to research questions on whether these models can be used to learn representations for different music cultures and styles, or whether we can build similar music audio embedding models trained on data from different cultures or styles. To that end, we leverage transfer learning methods to derive insights about the similarities between the different music cultures to which the data belongs to. We use two Western music datasets, two traditional/folk datasets coming from eastern Mediterranean cultures, and two datasets belonging to Indian art music. Three deep audio embedding models are trained and transferred across domains, including two CNN-based and a Transformer-based architecture, to perform auto-tagging for each target domain dataset. Experimental results show that competitive performance is achieved in all domains via transfer learning, while the best source dataset varies for each music culture. The implementation and the trained models are both provided in a public repository.
【5】 DisCover: Disentangled Music Representation Learning for Cover Song  Identification标题：DISCOVER：用于翻唱歌曲识别的解缠音乐表征学习链接：https://arxiv.org/abs/2307.09775
作者：Jiahao Xun,Shengyu Zhang,Yanting Yang,Jieming Zhu,Liqun Deng,Zhou Zhao,Zhenhua Dong,Ruiqi Li,Lichao Zhang,Fei Wu机构：Zhejiang University, Hangzhou, China, Huawei Noah’s Ark Lab, Shenzhen, China摘要：在音乐信息检索（MIR）领域，翻唱歌曲识别（CSI）是一项具有挑战性的任务，其目的是从海量的音乐收藏中识别出查询歌曲的翻唱版本。现有的作品仍然遭受高的歌曲内方差和歌曲间的相关性，由于纠缠的性质的特定版本和版本不变的因素在他们的建模。在这项工作中，我们设定的目标是解开特定版本和版本不变的因素，这可以使模型更容易地学习未知查询歌曲的不变的音乐表示。我们分析CSI任务在解纠缠的角度与因果图技术，并确定内部版本和内部版本的影响偏置不变学习。为了阻止这些影响，我们提出了解开音乐表征学习框架（Discover）CSI。Discoverer由两个关键组件组成：（1）知识引导的解纠缠模块（KDM）和（2）基于梯度的对抗解纠缠模块（GADM），其分别阻止版本内和版本间偏差效应。KDM最小化学习的表示和版本变化的因素之间的互信息，识别与先验的领域知识。GADM通过模拟歌曲内版本之间的表示转换来识别版本变化的因素，并利用对抗蒸馏的效果阻断。与性能最佳的方法进行了广泛的比较和深入的分析，证明了Discoverer的有效性和CSI解纠缠的必要性。摘要：In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collection. Existing works still suffer from high intra-song variances and inter-song correlations, due to the entangled nature of version-specific and version-invariant factors in their modeling. In this work, we set the goal of disentangling version-specific and version-invariant factors, which could make it easier for the model to learn invariant music representations for unseen query songs. We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning. To block these effects, we propose the disentangled music representation learning framework (DisCover) for CSI. DisCover consists of two critical components: (1) Knowledge-guided Disentanglement Module (KDM) and (2) Gradient-based Adversarial Disentanglement Module (GADM), which block intra-version and inter-version biased effects, respectively. KDM minimizes the mutual information between the learned representations and version-variant factors that are identified with prior domain knowledge. GADM identifies version-variant factors by simulating the representation transitions between intra-song versions, and exploits adversarial distillation for effect blocking. Extensive comparisons with best-performing methods and in-depth analysis demonstrate the effectiveness of DisCover and the and necessity of disentanglement for CSI.
【6】 Improving Domain Generalization for Sound Classification with Sparse  Frequency-Regularized Transformer标题：用稀疏频率正则化Transformer改进域泛化的声音分类链接：https://arxiv.org/abs/2307.09723
作者：Honglin Mu,Wentian Xia,Wanxiang Che机构：Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China备注：Accepted by ICME 2023摘要：声音分类模型的性能受到对分布外（OOD）数据的泛化的影响。已经提出了许多方法来帮助模型推广。然而，大多数算法要么引入推理开销，要么专注于持久的CNN变体，而Transformers已被证明在许多自然语言处理和计算机视觉任务中优于CNN。我们提出了FRITO，一种有效的正则化技术的Transformer的自我注意，以提高模型的泛化能力，通过限制每个序列位置的注意感受域沿频谱图的频率维度。实验表明，我们的方法可以帮助Transformer模型在TAU 2020和Nsynth数据集上实现SOTA泛化性能，同时节省20%的推理时间。摘要：Sound classification models' performance suffers from generalizing on out-of-distribution (OOD) data. Numerous methods have been proposed to help the model generalize. However, most either introduce inference overheads or focus on long-lasting CNN-variants, while Transformers has been proven to outperform CNNs on numerous natural language processing and computer vision tasks. We propose FRITO, an effective regularization technique on Transformer's self-attention, to improve the model's generalization ability by limiting each sequence position's attention receptive field along the frequency dimension on the spectrogram. Experiments show that our method helps Transformer models achieve SOTA generalization performance on TAU 2020 and Nsynth datasets while saving 20% inference time.
【7】 JAZZVAR: A Dataset of Variations found within Solo Piano Performances of  Jazz Standards for Music Overpainting标题：JAZZVAR：爵士乐音乐覆盖标准独奏钢琴演奏中的变奏数据集链接：https://arxiv.org/abs/2307.09670
作者：Eleanor Row,Jingjing Tang,George Fazekas机构：Centre for Digital Music, Queen Mary University of London备注：Pre-print accepted for publication at CMMR2023, 12 pages, 4 figures摘要：爵士钢琴家常常对爵士乐标准有独特的诠释。从这些解释的段落可以被看作是变异的部分。我们手动提取这样的变化从独奏爵士钢琴演奏。JAZZVAR数据集是502对Variation和Original MIDI片段的集合。数据集中的每个变奏都伴随着一个对应的原始片段，其中包含来自原始爵士乐标准的旋律和和弦。我们的方法不同于音乐信息检索（MIR）社区中的许多现有爵士乐数据集，这些数据集通常专注于爵士乐表演中的即兴部分。在本文中，我们概述了获得和排序曲目的策展过程，创建原始和变化对的管道，以及我们对数据集的分析。我们还介绍了一个新的生成音乐任务，音乐覆盖，并提出了一个基线Transformer模型训练的JAZZVAR数据集的这项任务。我们的数据集的其他潜在应用包括表达性能分析和表演者识别。摘要：Jazz pianists often uniquely interpret jazz standards. Passages from these interpretations can be viewed as sections of variation. We manually extracted such variations from solo jazz piano performances. The JAZZVAR dataset is a collection of 502 pairs of Variation and Original MIDI segments. Each Variation in the dataset is accompanied by a corresponding Original segment containing the melody and chords from the original jazz standard. Our approach differs from many existing jazz datasets in the music information retrieval (MIR) community, which often focus on improvisation sections within jazz performances. In this paper, we outline the curation process for obtaining and sorting the repertoire, the pipeline for creating the Original and Variation pairs, and our analysis of the dataset. We also introduce a new generative music task, Music Overpainting, and present a baseline Transformer model trained on the JAZZVAR dataset for this task. Other potential applications of our dataset include expressive performance analysis and performer identification.
机器翻译，仅供参考