今日论文合集：cs.SD语音6篇，eess.AS音频处理6篇。
cs.SD语音
【1】 Exploiting Diverse Feature for Multimodal Sentiment Analysis标题：利用多种特征进行多通道情感分析链接：https://arxiv.org/abs/2308.13421
作者：Jia Li,Wei Qian,Kun Li,Qi Li,Dan Guo,Meng Wang机构：Hefei University of Technology, Hefei, Anhui, China, Anhui University, Institute of Artificial Intelligence, Hefei Comprehensive National, Science Center摘要：在本文中，我们提出了我们的解决方案的MuSe个性化子挑战的MuSe 2023多模态情感分析挑战。MuSe个性化的任务旨在基于参与者的视听、语言和生理信号模态数据来预测参与者的连续唤醒和效价值。考虑到不同的人具有个人特征，该任务的主要挑战是如何建立用于情感预测的鲁棒性特征表示。为了解决这个问题，我们建议利用不同的功能。具体来说，我们提出了一系列的特征提取方法，以建立一个强大的表示和模型集成。我们经验性地评估所使用的方法在官方提供的数据集上的性能。\textbf{因此，我们在MuSe个性化子挑战赛中获得第三名。}具体而言，我们实现了0.8492和0.8439的结果MuSe个性化的唤醒和效价CCC。摘要：In this paper, we present our solution to the MuSe-Personalisation sub-challenge in the MuSe 2023 Multimodal Sentiment Analysis Challenge. The task of MuSe-Personalisation aims to predict the continuous arousal and valence values of a participant based on their audio-visual, language, and physiological signal modalities data. Considering different people have personal characteristics, the main challenge of this task is how to build robustness feature presentation for sentiment prediction. To address this issue, we propose exploiting diverse features. Specifically, we proposed a series of feature extraction methods to build a robust representation and model ensemble. We empirically evaluate the performance of the utilized method on the officially provided dataset. \textbf{As a result, we achieved 3rd place in the MuSe-Personalisation sub-challenge.} Specifically, we achieve the results of 0.8492 and 0.8439 for MuSe-Personalisation in terms of arousal and valence CCC.
【2】 Expressive paragraph text-to-speech synthesis with multi-step  variational autoencoder标题：基于多步变分自动编码器的表现型段落文语转换链接：https://arxiv.org/abs/2308.13365
作者：Xuyuan Li,Zengqiang Shang,Jian Liu,Hua Hua,Peiyang Shi,Pengyuan Zhang机构：♠ Laboratory of Speech and Intelligent Information Processing, Institute of Acoustics, CAS, China, † University of Chinese Academy of Sciences, China备注：5 pages, 1 figure, 2 tables摘要：神经网络已经能够生成具有高表达力的高质量单句语音。然而，它仍然是一个挑战，段落级的语音合成，由于需要连贯的声学特征，同时提供句子风格。同时，直接在超长语音上训练这些模型会降低合成质量。本文提出了一个高质量和表现力的段落语音合成系统与多步变分自动编码器。我们的方法采用多步潜变量来捕获语音信息，并预测他们与文本信息分别在不同的语法水平。我们还提出了一个三步训练方法，以促进性能的解耦过程。提出的TTS模型在暴雪挑战赛2023发布的单扬声器法语有声读物语料库上进行了训练。实验结果强调了我们的系统比基线模型的显着优势。摘要：Neural networks have been able to generate high-quality single-sentence speech with high expressiveness. However, it remains a challenge concerning paragraph-level speech synthesis due to the need for coherent acoustic features while delivering sentence styles. Meanwhile, training those models directly on over-length speech suffers from degrading synthesizing quality. This paper proposes a high-quality and expressive paragraph speech synthesis system with a multi-step variational autoencoder. Our approach employs multi-step latent variables to capture speech information and predicts them with text information separately at different grammatical levels. We also propose a three-step training method to promote the performance of the decoupling process. The proposed TTS model was trained on a single-speaker French audiobook corpus released at Blizzard Challenge 2023. Experimental results underscore the significant superiority of our system over baseline models.
【3】 Deep Active Audio Feature Learning in Resource-Constrained Environments标题：资源受限环境下的深度主动音频特征学习链接：https://arxiv.org/abs/2308.13201
作者：Md Mohaimenuzzaman,Christoph Bergmeir,Bernd Meyer机构：Department of Data Science and Artificial Intelligence, Monash, University, Australia., Department of Computer Science and Artificial Intelligence, University of Granada, Spain.摘要：标记数据的稀缺性使得在生物声学应用中训练深度神经网络（DNN）模型具有挑战性。在典型的生物声学应用中，手动标记所需的数据量可能是非常昂贵的。为了有效地识别新类和当前类，DNN模型必须继续从少量的新数据中学习新特征。主动学习（AL）是一种可以帮助这种学习的方法，同时需要很少的标签工作。然而，使用固定的特征提取方法限制了特征质量，导致AL的益处未得到充分利用。我们描述了一个AL框架，解决了这个问题，将特征提取到AL循环和细化后，每轮手动注释的特征提取器。此外，我们使用原始音频处理而不是频谱图，这是一种新颖的方法。实验表明，对于大型DNN模型，所提出的AL框架分别需要在基准音频数据集ESC-50，UrbanSound 8 k和InsectWingBeat上减少14.3%，66.7%和47.4%的标记工作，并且在基于微控制器的对应物上具有类似的节省。此外，我们通过纳入保护生物学项目的数据来展示我们研究的实际相关性。摘要：The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To effectively identify both new and current classes, DNN models must continue to learn new features from a modest amount of fresh data. Active Learning (AL) is an approach that can help with this learning while requiring little labelling effort. Nevertheless, the use of fixed feature extraction approaches limits feature quality, resulting in underutilization of the benefits of AL. We describe an AL framework that addresses this issue by incorporating feature extraction into the AL loop and refining the feature extractor after each round of manual annotation. In addition, we use raw audio processing rather than spectrograms, which is a novel approach. Experiments reveal that the proposed AL framework requires 14.3%, 66.7%, and 47.4% less labelling effort on benchmark audio datasets ESC-50, UrbanSound8k, and InsectWingBeat, respectively, for a large DNN model and similar savings on a microcontroller-based counterpart. Furthermore, we showcase the practical relevance of our study by incorporating data from conservation biology projects.
【4】 Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with  Disentangled Representations标题：解缠表示的泛化零发音自适应语音合成链接：https://arxiv.org/abs/2308.13007
作者：Wenbin Wang,Yang Song,Sanjay Jha机构：School of Computer Science and Engineering, University of New South Wales, Australia备注：5 pages, 3 figures. Accepted by Interspeech 2023, Oral摘要：虽然对语音合成的大多数研究都集中在为数据集内的说话者合成高质量语音，但同样重要但未解决的问题是为具有有限参考数据的数据集外的看不见的说话者合成语音，即，说话人自适应语音合成许多研究已经提出了zero-shot扬声器自适应文本到语音和语音转换方法，针对这一任务。然而，大多数当前方法在合成未看见的说话者的语音时遭受自然度和说话者相似性的退化（即，不在训练数据集中的说话者），这是由于模型在分布外数据中的较差的泛化性。为了解决这个问题，我们提出了GZS-TV，一个可推广的zero-shot扬声器自适应文本到语音和语音转换模型。GZS-TV引入了用于说话者嵌入提取和音色变换的解纠缠表示学习，以提高模型泛化，并利用变分自动编码器的表示学习能力来增强说话者编码器。我们的实验表明，GZS-TV减少了看不见的扬声器上的性能下降，并在多个数据集中优于所有基线模型。摘要：While most research into speech synthesis has focused on synthesizing high-quality speech for in-dataset speakers, an equally essential yet unsolved problem is synthesizing speech for unseen speakers who are out-of-dataset with limited reference data, i.e., speaker adaptive speech synthesis. Many studies have proposed zero-shot speaker adaptive text-to-speech and voice conversion approaches aimed at this task. However, most current approaches suffer from the degradation of naturalness and speaker similarity when synthesizing speech for unseen speakers (i.e., speakers not in the training dataset) due to the poor generalizability of the model in out-of-distribution data. To address this problem, we propose GZS-TV, a generalizable zero-shot speaker adaptive text-to-speech and voice conversion model. GZS-TV introduces disentangled representation learning for both speaker embedding extraction and timbre transformation to improve model generalization and leverages the representation learning capability of the variational autoencoder to enhance the speaker encoder. Our experiments demonstrate that GZS-TV reduces performance degradation on unseen speakers and outperforms all baseline models in multiple datasets.
【5】 A Survey of AI Music Generation Tools and Models标题：人工智能音乐生成工具和模型综述链接：https://arxiv.org/abs/2308.12982
作者：Yueyue Zhu,Jared Baca,Banafsheh Rekabdar,Reza Rawassizadeh摘要：在这项工作中，我们提供了一个全面的调查人工智能音乐生成工具，包括研究项目和商业化的应用。为了进行我们的分析，我们将音乐生成方法分为三类：基于参数、基于文本和基于视觉的类。我们的调查强调了这些工具的各种可能性和功能特点，这些工具迎合了广泛的用户，从普通听众到专业音乐家。我们观察到，每种工具都有自己的优点和局限性。因此，我们编制了一份工具选择过程中应考虑的这些因素的综合清单。此外，我们的调查为人工智能音乐生成的潜在机制和挑战提供了重要见解。摘要：In this work, we provide a comprehensive survey of AI music generation tools, including both research projects and commercialized applications. To conduct our analysis, we classified music generation approaches into three categories: parameter-based, text-based, and visual-based classes. Our survey highlights the diverse possibilities and functional features of these tools, which cater to a wide range of users, from regular listeners to professional musicians. We observed that each tool has its own set of advantages and limitations. As a result, we have compiled a comprehensive list of these factors that should be considered during the tool selection process. Moreover, our survey offers critical insights into the underlying mechanisms and challenges of AI music generation.
【6】 Decoupled Structure for Improved Adaptability of End-to-End Models标题：用于改进端到端模型适应性的解耦结构链接：https://arxiv.org/abs/2308.13345
作者：Keqi Deng,Philip C. Woodland机构：Department of Engineering, University of Cambridge, Trumpington Street, Cambridge, CB,PZ, UK, A R T I C L E I N F O摘要：虽然端到端（E2 E）可训练自动语音识别（ASR）通过联合学习声学和语言信息已经显示出巨大的成功，但是它仍然遭受域移位的影响，从而限制了潜在的应用。E2 E ASR模型隐式地学习内部语言模型LM描述了源域的训练分布，而E2 E的可训练性使得内部LM难以适应纯文本数据的目标域。为了解决这个问题，本文提出了基于注意力的编码器-解码器的解耦结构（解耦AED）和神经换能器（解耦换能器）模型，其可以在离线和在线场景中实现灵活的域适应，同时保持稳健的域内性能。为此，E2 E模型解码器（或预测网络）的声学和语言部分被解耦，使得语言分量（即，语音分量）被分离。内部LM）可更换。当遇到域移位时，内部LM可以在推断期间由目标域LM直接替换，而无需重新训练或使用特定于域的配对语音-文本数据。在LibriSpeech-100 h语料库上训练的E2 E ASR模型的实验表明，所提出的解耦结构在TED-LIUM 2和AESRC 2020语料库上分别降低了15.1%和17.2%的相对单词错误率，同时仍然保持了域内数据的性能。摘要：Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications. The E2E ASR model implicitly learns an internal language model (LM) which characterises the training distribution of the source domain, and the E2E trainable nature makes the internal LM difficult to adapt to the target domain with text-only data To solve this problem, this paper proposes decoupled structures for attention-based encoder-decoder (Decoupled-AED) and neural transducer (Decoupled-Transducer) models, which can achieve flexible domain adaptation in both offline and online scenarios while maintaining robust intra-domain performance. To this end, the acoustic and linguistic parts of the E2E model decoder (or prediction network) are decoupled, making the linguistic component (i.e. internal LM) replaceable. When encountering a domain shift, the internal LM can be directly replaced during inference by a target-domain LM, without re-training or using domain-specific paired speech-text data. Experiments for E2E ASR models trained on the LibriSpeech-100h corpus showed that the proposed decoupled structure gave 15.1% and 17.2% relative word error rate reductions on the TED-LIUM 2 and AESRC2020 corpora while still maintaining performance on intra-domain data.
eess.AS音频处理
【1】 Decoupled Structure for Improved Adaptability of End-to-End Models标题：用于改进端到端模型适应性的解耦结构链接：https://arxiv.org/abs/2308.13345
作者：Keqi Deng,Philip C. Woodland机构：Department of Engineering, University of Cambridge, Trumpington Street, Cambridge, CB,PZ, UK, A R T I C L E I N F O摘要：虽然端到端（E2 E）可训练自动语音识别（ASR）通过联合学习声学和语言信息已经显示出巨大的成功，但是它仍然遭受域移位的影响，从而限制了潜在的应用。E2 E ASR模型隐式地学习内部语言模型LM描述了源域的训练分布，而E2 E的可训练性使得内部LM难以适应纯文本数据的目标域。为了解决这个问题，本文提出了基于注意力的编码器-解码器的解耦结构（解耦AED）和神经换能器（解耦换能器）模型，其可以在离线和在线场景中实现灵活的域适应，同时保持稳健的域内性能。为此，E2 E模型解码器（或预测网络）的声学和语言部分被解耦，使得语言分量（即，语音分量）被分离。内部LM）可更换。当遇到域移位时，内部LM可以在推断期间由目标域LM直接替换，而无需重新训练或使用特定于域的配对语音-文本数据。在LibriSpeech-100 h语料库上训练的E2 E ASR模型的实验表明，所提出的解耦结构在TED-LIUM 2和AESRC 2020语料库上分别降低了15.1%和17.2%的相对单词错误率，同时仍然保持了域内数据的性能。摘要：Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications. The E2E ASR model implicitly learns an internal language model (LM) which characterises the training distribution of the source domain, and the E2E trainable nature makes the internal LM difficult to adapt to the target domain with text-only data To solve this problem, this paper proposes decoupled structures for attention-based encoder-decoder (Decoupled-AED) and neural transducer (Decoupled-Transducer) models, which can achieve flexible domain adaptation in both offline and online scenarios while maintaining robust intra-domain performance. To this end, the acoustic and linguistic parts of the E2E model decoder (or prediction network) are decoupled, making the linguistic component (i.e. internal LM) replaceable. When encountering a domain shift, the internal LM can be directly replaced during inference by a target-domain LM, without re-training or using domain-specific paired speech-text data. Experiments for E2E ASR models trained on the LibriSpeech-100h corpus showed that the proposed decoupled structure gave 15.1% and 17.2% relative word error rate reductions on the TED-LIUM 2 and AESRC2020 corpora while still maintaining performance on intra-domain data.
【2】 Exploiting Diverse Feature for Multimodal Sentiment Analysis标题：利用多种特征进行多通道情感分析链接：https://arxiv.org/abs/2308.13421
作者：Jia Li,Wei Qian,Kun Li,Qi Li,Dan Guo,Meng Wang机构：Hefei University of Technology, Hefei, Anhui, China, Anhui University, Institute of Artificial Intelligence, Hefei Comprehensive National, Science Center摘要：在本文中，我们提出了我们的解决方案的MuSe个性化子挑战的MuSe 2023多模态情感分析挑战。MuSe个性化的任务旨在基于参与者的视听、语言和生理信号模态数据来预测参与者的连续唤醒和效价值。考虑到不同的人具有个人特征，该任务的主要挑战是如何建立用于情感预测的鲁棒性特征表示。为了解决这个问题，我们建议利用不同的功能。具体来说，我们提出了一系列的特征提取方法，以建立一个强大的表示和模型集成。我们经验性地评估所使用的方法在官方提供的数据集上的性能。\textbf{因此，我们在MuSe个性化子挑战赛中获得第三名。}具体而言，我们实现了0.8492和0.8439的结果MuSe个性化的唤醒和效价CCC。摘要：In this paper, we present our solution to the MuSe-Personalisation sub-challenge in the MuSe 2023 Multimodal Sentiment Analysis Challenge. The task of MuSe-Personalisation aims to predict the continuous arousal and valence values of a participant based on their audio-visual, language, and physiological signal modalities data. Considering different people have personal characteristics, the main challenge of this task is how to build robustness feature presentation for sentiment prediction. To address this issue, we propose exploiting diverse features. Specifically, we proposed a series of feature extraction methods to build a robust representation and model ensemble. We empirically evaluate the performance of the utilized method on the officially provided dataset. \textbf{As a result, we achieved 3rd place in the MuSe-Personalisation sub-challenge.} Specifically, we achieve the results of 0.8492 and 0.8439 for MuSe-Personalisation in terms of arousal and valence CCC.
【3】 Expressive paragraph text-to-speech synthesis with multi-step  variational autoencoder标题：基于多步变分自动编码器的表现型段落文语转换链接：https://arxiv.org/abs/2308.13365
作者：Xuyuan Li,Zengqiang Shang,Jian Liu,Hua Hua,Peiyang Shi,Pengyuan Zhang机构：♠ Laboratory of Speech and Intelligent Information Processing, Institute of Acoustics, CAS, China, † University of Chinese Academy of Sciences, China备注：5 pages, 1 figure, 2 tables摘要：神经网络已经能够生成具有高表达力的高质量单句语音。然而，它仍然是一个挑战，段落级的语音合成，由于需要连贯的声学特征，同时提供句子风格。同时，直接在超长语音上训练这些模型会降低合成质量。本文提出了一个高质量和表现力的段落语音合成系统与多步变分自动编码器。我们的方法采用多步潜变量来捕获语音信息，并预测他们与文本信息分别在不同的语法水平。我们还提出了一个三步训练方法，以促进性能的解耦过程。提出的TTS模型在暴雪挑战赛2023发布的单扬声器法语有声读物语料库上进行了训练。实验结果强调了我们的系统比基线模型的显着优势。摘要：Neural networks have been able to generate high-quality single-sentence speech with high expressiveness. However, it remains a challenge concerning paragraph-level speech synthesis due to the need for coherent acoustic features while delivering sentence styles. Meanwhile, training those models directly on over-length speech suffers from degrading synthesizing quality. This paper proposes a high-quality and expressive paragraph speech synthesis system with a multi-step variational autoencoder. Our approach employs multi-step latent variables to capture speech information and predicts them with text information separately at different grammatical levels. We also propose a three-step training method to promote the performance of the decoupling process. The proposed TTS model was trained on a single-speaker French audiobook corpus released at Blizzard Challenge 2023. Experimental results underscore the significant superiority of our system over baseline models.
【4】 Deep Active Audio Feature Learning in Resource-Constrained Environments标题：资源受限环境下的深度主动音频特征学习链接：https://arxiv.org/abs/2308.13201
作者：Md Mohaimenuzzaman,Christoph Bergmeir,Bernd Meyer机构：Department of Data Science and Artificial Intelligence, Monash, University, Australia., Department of Computer Science and Artificial Intelligence, University of Granada, Spain.摘要：标记数据的稀缺性使得在生物声学应用中训练深度神经网络（DNN）模型具有挑战性。在典型的生物声学应用中，手动标记所需的数据量可能是非常昂贵的。为了有效地识别新类和当前类，DNN模型必须继续从少量的新数据中学习新特征。主动学习（AL）是一种可以帮助这种学习的方法，同时需要很少的标签工作。然而，使用固定的特征提取方法限制了特征质量，导致AL的益处未得到充分利用。我们描述了一个AL框架，解决了这个问题，将特征提取到AL循环和细化后，每轮手动注释的特征提取器。此外，我们使用原始音频处理而不是频谱图，这是一种新颖的方法。实验表明，对于大型DNN模型，所提出的AL框架分别需要在基准音频数据集ESC-50，UrbanSound 8 k和InsectWingBeat上减少14.3%，66.7%和47.4%的标记工作，并且在基于微控制器的对应物上具有类似的节省。此外，我们通过纳入保护生物学项目的数据来展示我们研究的实际相关性。摘要：The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To effectively identify both new and current classes, DNN models must continue to learn new features from a modest amount of fresh data. Active Learning (AL) is an approach that can help with this learning while requiring little labelling effort. Nevertheless, the use of fixed feature extraction approaches limits feature quality, resulting in underutilization of the benefits of AL. We describe an AL framework that addresses this issue by incorporating feature extraction into the AL loop and refining the feature extractor after each round of manual annotation. In addition, we use raw audio processing rather than spectrograms, which is a novel approach. Experiments reveal that the proposed AL framework requires 14.3%, 66.7%, and 47.4% less labelling effort on benchmark audio datasets ESC-50, UrbanSound8k, and InsectWingBeat, respectively, for a large DNN model and similar savings on a microcontroller-based counterpart. Furthermore, we showcase the practical relevance of our study by incorporating data from conservation biology projects.
【5】 Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with  Disentangled Representations标题：解缠表示的泛化零发音自适应语音合成链接：https://arxiv.org/abs/2308.13007
作者：Wenbin Wang,Yang Song,Sanjay Jha机构：School of Computer Science and Engineering, University of New South Wales, Australia备注：5 pages, 3 figures. Accepted by Interspeech 2023, Oral摘要：虽然对语音合成的大多数研究都集中在为数据集内的说话者合成高质量语音，但同样重要但未解决的问题是为具有有限参考数据的数据集外的看不见的说话者合成语音，即，说话人自适应语音合成许多研究已经提出了zero-shot扬声器自适应文本到语音和语音转换方法，针对这一任务。然而，大多数当前方法在合成未看见的说话者的语音时遭受自然度和说话者相似性的退化（即，不在训练数据集中的说话者），这是由于模型在分布外数据中的较差的泛化性。为了解决这个问题，我们提出了GZS-TV，一个可推广的zero-shot扬声器自适应文本到语音和语音转换模型。GZS-TV引入了用于说话者嵌入提取和音色变换的解纠缠表示学习，以提高模型泛化，并利用变分自动编码器的表示学习能力来增强说话者编码器。我们的实验表明，GZS-TV减少了看不见的扬声器上的性能下降，并在多个数据集中优于所有基线模型。摘要：While most research into speech synthesis has focused on synthesizing high-quality speech for in-dataset speakers, an equally essential yet unsolved problem is synthesizing speech for unseen speakers who are out-of-dataset with limited reference data, i.e., speaker adaptive speech synthesis. Many studies have proposed zero-shot speaker adaptive text-to-speech and voice conversion approaches aimed at this task. However, most current approaches suffer from the degradation of naturalness and speaker similarity when synthesizing speech for unseen speakers (i.e., speakers not in the training dataset) due to the poor generalizability of the model in out-of-distribution data. To address this problem, we propose GZS-TV, a generalizable zero-shot speaker adaptive text-to-speech and voice conversion model. GZS-TV introduces disentangled representation learning for both speaker embedding extraction and timbre transformation to improve model generalization and leverages the representation learning capability of the variational autoencoder to enhance the speaker encoder. Our experiments demonstrate that GZS-TV reduces performance degradation on unseen speakers and outperforms all baseline models in multiple datasets.
【6】 A Survey of AI Music Generation Tools and Models标题：人工智能音乐生成工具和模型综述链接：https://arxiv.org/abs/2308.12982
作者：Yueyue Zhu,Jared Baca,Banafsheh Rekabdar,Reza Rawassizadeh摘要：在这项工作中，我们提供了一个全面的调查人工智能音乐生成工具，包括研究项目和商业化的应用。为了进行我们的分析，我们将音乐生成方法分为三类：基于参数、基于文本和基于视觉的类。我们的调查强调了这些工具的各种可能性和功能特点，这些工具迎合了广泛的用户，从普通听众到专业音乐家。我们观察到，每种工具都有自己的优点和局限性。因此，我们编制了一份工具选择过程中应考虑的这些因素的综合清单。此外，我们的调查为人工智能音乐生成的潜在机制和挑战提供了重要见解。摘要：In this work, we provide a comprehensive survey of AI music generation tools, including both research projects and commercialized applications. To conduct our analysis, we classified music generation approaches into three categories: parameter-based, text-based, and visual-based classes. Our survey highlights the diverse possibilities and functional features of these tools, which cater to a wide range of users, from regular listeners to professional musicians. We observed that each tool has its own set of advantages and limitations. As a result, we have compiled a comprehensive list of these factors that should be considered during the tool selection process. Moreover, our survey offers critical insights into the underlying mechanisms and challenges of AI music generation.
机器翻译，仅供参考