今日论文合集：cs.SD语音1篇，eess.AS音频处理2篇。
【1】 Rock Guitar Tablature Generation via Natural Language Processing
标题：基于自然语言处理的摇滚吉他表格化生成
链接：https://arxiv.org/abs/2301.05295
机构：Rice University, Houston, TX, USA摘要：深度学习最近使图像和文本的生成式建模变得更加强大和民主化，同时还有其他并行工作探索生成更复杂形式的数据（如音频）的可能性。然而，目前音频和音乐的高维度、长范围依赖性和缺乏标准化数据集使得生成式建模非常具有挑战性。我们建议将音乐建模为一系列离散的音符，在这些音符上，我们可以使用自回归自然语言处理技术来成功地进行生成建模。虽然以前的作品使用类似的管道数据，如乐谱和MIDI，我们的目标是扩大这种方法的研究不足的媒介吉他指法。具体地说，我们开发了我们所知的第一个工作，模型一个特定的流派作为吉他指法：重摇滚乐。不像其他作品在吉他指法生成，我们有一个免费的公共演示在https://huggingface.co/spaces/josuelmet/Metal_Music_Interpolator摘要：Deep learning has recently empowered and democratized generative modeling of images and text, with additional concurrent works exploring the possibility of generating more complex forms of data, such as audio. However, the high dimensionality, long-range dependencies, and lack of standardized datasets currently makes generative modeling of audio and music very challenging. We propose to model music as a series of discrete notes upon which we can use autoregressive natural language processing techniques for successful generative modeling. While previous works used similar pipelines on data such as sheet music and MIDI, we aim to extend such approaches to the under-studied medium of guitar tablature. Specifically, we develop the first work to our knowledge that models one specific genre as guitar tablature: heavy rock. Unlike other works in guitar tablature generation, we have a freely available public demo at https://huggingface.co/spaces/josuelmet/Metal_Music_Interpolator
【1】 Multilingual Alzheimer's Dementia Recognition through Spontaneous Speech: a Signal Processing Grand Challenge
标题：通过自发语音进行多语言阿尔茨海默病识别：信号处理的巨大挑战
链接：https://arxiv.org/abs/2301.05562
作者：Saturnino Luz,Fasih Haider,Davida Fromm,Ioulietta Lazarou,Ioannis Kompatsiaris,Brian MacWhinney机构：Usher Institute, Edinburgh Medical School, The University of Edinburgh, UK, Department of Psychology, Carnegie Mellon University, USA, Information Technologies Institute, CERTH, Thermi-Thessaloniki, Greece备注：ICASSP 2023 SPGC description摘要：这个信号处理大挑战赛（SPGC）针对社会和医学相关性的困难的自动预测问题，即阿尔茨海默氏痴呆（AD）的检测。参与者被邀请采用信号处理和机器学习方法来创建基于自发语音数据的预测模型。该挑战旨在评估基于一种语言（英语）的语音构建的预测模型推广到另一种语言（希腊语）的程度。就我们所知，还没有研究在多语言AD检测中语音信号的声学特征的工作。我们的基线系统使用传统的机器学习算法和声学特征的主动数据表示，实现了73.91%的AD检测准确率和4.95的认知评分预测均方根误差。摘要：This Signal Processing Grand Challenge (SPGC) targets a difficult automatic prediction problem of societal and medical relevance, namely, the detection of Alzheimer's Dementia (AD). Participants were invited to employ signal processing and machine learning methods to create predictive models based on spontaneous speech data. The Challenge has been designed to assess the extent to which predictive models built based on speech in one language (English) generalise to another language (Greek). To the best of our knowledge no work has investigated acoustic features of the speech signal in multilingual AD detection. Our baseline system used conventional machine learning algorithms with Active Data Representation of acoustic features, achieving accuracy of 73.91% on AD detection, and 4.95 root mean squared error on cognitive score prediction.
【2】 Rock Guitar Tablature Generation via Natural Language Processing
标题：基于自然语言处理的摇滚吉他表格化生成
链接：https://arxiv.org/abs/2301.05295
*与cs.SD语音【1】为同一篇
机构：Rice University, Houston, TX, USA摘要：深度学习最近使图像和文本的生成式建模变得更加强大和民主化，同时还有其他并行工作探索生成更复杂形式的数据（如音频）的可能性。然而，目前音频和音乐的高维度、长范围依赖性和缺乏标准化数据集使得生成式建模非常具有挑战性。我们建议将音乐建模为一系列离散的音符，在这些音符上，我们可以使用自回归自然语言处理技术来成功地进行生成建模。虽然以前的作品使用类似的管道数据，如乐谱和MIDI，我们的目标是扩大这种方法的研究不足的媒介吉他指法。具体地说，我们开发了我们所知的第一个工作，模型一个特定的流派作为吉他指法：重摇滚乐。不像其他作品在吉他指法生成，我们有一个免费的公共演示在https://huggingface.co/spaces/josuelmet/Metal_Music_Interpolator摘要：Deep learning has recently empowered and democratized generative modeling of images and text, with additional concurrent works exploring the possibility of generating more complex forms of data, such as audio. However, the high dimensionality, long-range dependencies, and lack of standardized datasets currently makes generative modeling of audio and music very challenging. We propose to model music as a series of discrete notes upon which we can use autoregressive natural language processing techniques for successful generative modeling. While previous works used similar pipelines on data such as sheet music and MIDI, we aim to extend such approaches to the under-studied medium of guitar tablature. Specifically, we develop the first work to our knowledge that models one specific genre as guitar tablature: heavy rock. Unlike other works in guitar tablature generation, we have a freely available public demo at https://huggingface.co/spaces/josuelmet/Metal_Music_Interpolator
机器翻译，仅供参考
每日语音速递