今日论文合集：cs.SD语音6篇，eess.AS音频处理6篇。
【1】 Multimodal Emotion Recognition among Couples from Lab Settings to Daily Life using Smartwatches
标题：使用智能手表从实验室环境到日常生活的夫妻多模式情感识别
链接：https://arxiv.org/abs/2212.13917
备注：PhD Thesis, 2022 - ETH Zurich摘要：夫妻通常一起管理慢性病，这种管理对病人和他们的浪漫伴侣都造成了情感上的损失。因此，认识每一个伴侣在日常生活中的情绪可以提供一个洞察他们的情绪健康在慢性病管理。目前在实验室和日常生活中使用自我报告或观察者报告来推断伴侣的情绪，自我报告对于连续情绪评估是不实用的，观察者报告是手动的、时间密集的并且成本高。目前，关于夫妻间情绪识别的研究尚缺乏全面的综述。此外，用于夫妇之间的情感识别的方法（1）集中于美国的讲英语的夫妇，(2)使用从实验室收集的数据，以及（3）使用观察者评级而不是伴侣的自我报告/主观情绪来执行识别。在本论文所包含的这部分工作中（8篇论文-- 5篇已发表，3篇正在各种期刊上进行综述），我们填补了目前关于夫妻情感识别的文献空白，利用来自1，051个个体的161小时的数据开发了情感识别系统，并为将夫妻情感识别从实验室的现状带到日常生活中做出了贡献。本论文致力于建立自动化的情绪识别系统，最终使伴侣能够在日常生活中监测他们的情绪，并能够提供干预措施，以改善他们的情绪健康。摘要：Couples generally manage chronic diseases together and the management takes an emotional toll on both patients and their romantic partners. Consequently, recognizing the emotions of each partner in daily life could provide an insight into their emotional well-being in chronic disease management. The emotions of partners are currently inferred in the lab and daily life using self-reports which are not practical for continuous emotion assessment or observer reports which are manual, time-intensive, and costly. Currently, there exists no comprehensive overview of works on emotion recognition among couples. Furthermore, approaches for emotion recognition among couples have (1) focused on English-speaking couples in the U.S., (2) used data collected from the lab, and (3) performed recognition using observer ratings rather than partner's self-reported / subjective emotions. In this body of work contained in this thesis (8 papers - 5 published and 3 currently under review in various journals), we fill the current literature gap on couples' emotion recognition, develop emotion recognition systems using 161 hours of data from a total of 1,051 individuals, and make contributions towards taking couples' emotion recognition from the lab which is the status quo, to daily life. This thesis contributes toward building automated emotion recognition systems that would eventually enable partners to monitor their emotions in daily life and enable the delivery of interventions to improve their emotional well-being.
【2】 Voice conversion with limited data and limitless data augmentations
标题：有限数据和无限数据扩充的语音转换
链接：https://arxiv.org/abs/2212.13581
作者：Olga Slizovskaia,Jordi Janer,Pritish Chandna,Oscar Mayor摘要：对输入语音信号施加改变以将感知的语音说话者改变为目标，同时保持输入的内容是一项具有挑战性但有趣的任务，称为话音转换（VC）。在过去的几年中，这项任务已经获得了极大的兴趣，其中大多数系统使用数据驱动的机器学习模型。在低延迟的真实场景中进行转换更具有挑战性，因为高质量数据的可用性受到限制。诸如音调移位和噪声添加之类的数据扩充经常用于增加用于训练该任务的基于机器学习的模型的数据量。在本文中，我们探讨了用于实时语音转换的常见数据增强技术的功效，并介绍了基于音频和语音变换效果的数据增强新技术。我们使用客观和主观的评价方法来评价男性和女性目标说话人的转换。摘要：Applying changes to an input speech signal to change the perceived speaker of speech to a target while maintaining the content of the input is a challenging but interesting task known as Voice conversion (VC). Over the last few years, this task has gained significant interest where most systems use data-driven machine learning models. Doing the conversion in a low-latency real-world scenario is even more challenging constrained by the availability of high-quality data. Data augmentations such as pitch shifting and noise addition are often used to increase the amount of data used for training machine learning based models for this task. In this paper we explore the efficacy of common data augmentation techniques for real-time voice conversion and introduce novel techniques for data augmentation based on audio and voice transformation effects as well. We evaluate the conversions for both male and female target speakers using objective and subjective evaluation methodologies.
【3】 Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation
标题：不要太过于自信!利用置信度松弛提高ASR译码性能
链接：https://arxiv.org/abs/2212.13378
作者：Tomer Wullach,Shlomo E. Chazan摘要：自动语音识别（ASR）系统经常使用基于搜索的解码策略，旨在通过考虑多个候选来找到最佳可获得的抄本。一个突出的语音识别解码试探法是波束搜索，其寻找具有使用预测分布计算的最大似然性的抄本。虽然在各种任务中表现出实质性的性能增益，但是当预测概率高度可信时，即，预测的分布集中在单个或非常少的类别。我们表明，最近提出的自我监督学习（SSL）为基础的ASR模型往往产生异常自信的预测，可能会阻碍波束搜索从真正考虑一个多样化的候选集。我们执行一个层次分析来揭示和可视化预测如何演变，并提出一个解码过程，提高了微调ASR模型的性能。我们提出的方法不需要超出原始微调的进一步训练，也不需要额外的模型参数。事实上，我们发现我们所提出的方法比现有方法需要更少的推理计算。我们建议聚合前M层，潜在地利用中间层中编码的有用信息，并放松模型置信度。我们通过对不同数量的标记资源和不同的模型大小进行实证研究来证明我们的方法的有效性，特别是当应用于低资源场景时，显示出一致的改进。摘要：Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search, which seeks the transcript with the greatest likelihood computed using the predicted distribution. While showing substantial performance gains in various tasks, beam search loses some of its effectiveness when the predicted probabilities are highly confident, i.e., the predicted distribution is massed for a single or very few classes. We show that recently proposed Self-Supervised Learning (SSL)-based ASR models tend to yield exceptionally confident predictions that may hamper beam search from truly considering a diverse set of candidates. We perform a layer analysis to reveal and visualize how predictions evolve, and propose a decoding procedure that improves the performance of fine-tuned ASR models. Our proposed approach does not require further training beyond the original fine-tuning, nor additional model parameters. In fact, we find that our proposed method requires significantly less inference computation than current approaches. We propose aggregating the top M layers, potentially leveraging useful information encoded in intermediate layers, and relaxing model confidence. We demonstrate the effectiveness of our approach by conducting an empirical study on varying amounts of labeled resources and different model sizes, showing consistent improvements in particular when applied to low-resource scenarios.
【4】 Feature Selection Approaches for Optimising Music Emotion Recognition Methods
标题：优化音乐情感识别方法的特征选择方法
链接：https://arxiv.org/abs/2212.13369
作者：Le Cai,Sam Ferguson,Haiyan Lu,Gengfa Fang摘要：特征的高维度是音乐情感识别的一个挑战。关于音频特征和情感之间的关系没有共同的共识。MER系统使用所有可用的特征来识别情感;然而，由于其包含充当噪声的不相关数据，因此这不是最佳解决方案。本文提出了一种特征选择方法来消除多目标匹配中的冗余特征。我们基于特征选择算法（FSA）创建了一个选定特征集（SFS），并通过使用两个模型（支持向量回归（SVR）和随机森林（RF））进行训练，并将其与使用完整特征集（CFS）进行比较来对其进行基准测试。实验结果表明，SFS的引入提高了随机森林（RF）和支持向量回归（SVR）模型的MER性能。我们发现使用FSA可以在所有场景下提高性能，并且它对MER任务的模型效率和稳定性具有潜在的好处。摘要：The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion; however, this is not an optimal solution since it contains irrelevant data acting as noise. In this paper, we introduce a feature selection approach to eliminate redundant features for MER. We created a Selected Feature Set (SFS) based on the feature selection algorithm (FSA) and benchmarked it by training with two models, Support Vector Regression (SVR) and Random Forest (RF) and comparing them against with using the Complete Feature Set (CFS). The result indicates that the performance of MER has improved for both Random Forest (RF) and Support Vector Regression (SVR) models by using SFS. We found using FSA can improve performance in all scenarios, and it has potential benefits for model efficiency and stability for MER task.
【5】 Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism
标题：基于音符位置感知注意机制的歌声合成
链接：https://arxiv.org/abs/2212.13703
作者：Yukiya Hono,Kei Hashimoto,Yoshihiko Nankaku,Keiichi Tokuda备注：5 pages, 4 figures, 2 tables, submitted to ICASSP 2023摘要：提出了一种新的具有音符位置感知注意机制的序列到序列（seq 2seq）模型用于歌声合成（SVS）。能够同时执行声学和时间建模的seq 2seq建模方法是有吸引力的。然而，由于歌唱声音的时间建模的困难，许多具有基于编码器-解码器的模型的最近SVS系统仍然显式地依赖于由附加模块生成的持续时间信息。虽然一些研究使用具有注意机制的seq 2seq模型执行同时建模，但是它们对于时间建模的鲁棒性不足。所提出的注意力机制被设计为通过考虑乐谱所给出的节奏来估计注意力权重。此外，还介绍了几种技术来提高歌声的建模性能。实验结果表明，该模型在定时的自然度和鲁棒性方面都是有效的。摘要：This paper proposes a novel sequence-to-sequence (seq2seq) model with a musical note position-aware attention mechanism for singing voice synthesis (SVS). A seq2seq modeling approach that can simultaneously perform acoustic and temporal modeling is attractive. However, due to the difficulty of the temporal modeling of singing voices, many recent SVS systems with an encoder-decoder-based model still rely on explicitly on duration information generated by additional modules. Although some studies perform simultaneous modeling using seq2seq models with an attention mechanism, they have insufficient robustness against temporal modeling. The proposed attention mechanism is designed to estimate the attention weights by considering the rhythm given by the musical score. Furthermore, several techniques are also introduced to improve the modeling performance of the singing voice. Experimental results indicated that the proposed model is effective in terms of both naturalness and robustness of timing.
【6】 Audiovisual Database with 360 Video and Higher-Order Ambisonics Audio for Perception, Cognition, Behavior, and QoE Evaluation Research
标题：360视频视听数据库和高阶两用音响对感知、认知、行为和QOE评价的研究
链接：https://arxiv.org/abs/2212.13442
作者：Thomas Robotham,Ashutosh Singla,Olli S. Rummukainen,Alexander Raake,Emanuël A. P. Habets备注：6 pages, 2 figures, accepted and presented at the 2022 14th International Conference on Quality of Multimedia Experience (QoMEX). Database is publicly accessible at this https URL摘要：对多模态感知、人类认知、行为和注意力的研究可以受益于高保真内容，当在头戴式显示器上呈现时，高保真内容可以再现类似真实生活的场景。此外，视听感知、认知过程和行为等方面可以补充基于问卷的交互式虚拟环境体验质量（QoE）评估。当前，缺乏可用于评估能够再现高质量内容的这些方面或系统的高质量开源视听数据库。通过本文，我们提供了一个公开的视听数据库，其中包含12个捕捉真实自然和城市环境的场景，视频分辨率为7680 x3840，每秒60帧，并带有4阶Ambisonics音频。这360个视频序列，平均持续时间为60秒，代表了用于系统评估单/多模态感知、认知、行为和QoE的各个维度的现实生活设置。本文详细介绍了场景要求、录制方法和场景描述。该数据库提供了高质量的参考材料，平衡地侧重于听觉和视觉感官信息。该数据库将不断更新，增加场景和其他元数据，如人的评分和显著性信息。摘要：Research into multi-modal perception, human cognition, behavior, and attention can benefit from high-fidelity content that may recreate real-life-like scenes when rendered on head-mounted displays. Moreover, aspects of audiovisual perception, cognitive processes, and behavior may complement questionnaire-based Quality of Experience (QoE) evaluation of interactive virtual environments. Currently, there is a lack of high-quality open-source audiovisual databases that can be used to evaluate such aspects or systems capable of reproducing high-quality content. With this paper, we provide a publicly available audiovisual database consisting of twelve scenes capturing real-life nature and urban environments with a video resolution of 7680x3840 at 60 frames-per-second and with 4th-order Ambisonics audio. These 360 video sequences, with an average duration of 60 seconds, represent real-life settings for systematically evaluating various dimensions of uni-/multi-modal perception, cognition, behavior, and QoE. The paper provides details of the scene requirements, recording approach, and scene descriptions. The database provides high-quality reference material with a balanced focus on auditory and visual sensory information. The database will be continuously updated with additional scenes and further metadata such as human ratings and saliency information.【1】 Distributed Active Noise Control System Based on a Block Diffusion FxLMS Algorithm with Bidirectional Communication
标题：基于双向通信块扩散FxLMS算法的分布式有源噪声控制系统
链接：https://arxiv.org/abs/2212.13777
作者：Tianyou Li,Hongji Duan,Sipei Zhao,Jing Lu,Ian S. Burnett摘要：近年来，基于扩散自适应的分布式有源噪声控制系统由于其与传统的集中式和分散式自适应方案相比在计算复杂度和稳定性之间的平衡而引起了极大的研究兴趣。然而，现有的扩散FxLMS算法采用节点特定的自适应和邻域范围的合并，并且假设邻居节点的控制滤波器彼此相似。这种假设在实际应用中是不正确的，并且它导致比集中式控制器方法差的性能。相比之下，本文提出了一种双向通信的块扩散FxLMS算法，该算法使用邻域自适应和节点特定组合来更新控制滤波器。仿真结果表明，该算法收敛于集中控制器的解，且计算量小。摘要：Recently, distributed active noise control systems based on diffusion adaptation have attracted significant research interest due to their balance between computational complexity and stability compared to conventional centralized and decentralized adaptation schemes. However, the existing diffusion FxLMS algorithm employs node-specific adaptation and neighborhood-wide combination, and assumes that the control filters of neighbor nodes are similar to each other. This assumption is not true in practical applications, and it leads to inferior performance to the centralized controller approach. In contrast, this paper proposes a Block Diffusion FxLMS algorithm with bidirectional communication, which uses neighborhood-wide adaptation and node-specific combination to update the control filters. Simulation results validate that the proposed algorithm converges to the solution of the centralized controller with reduced computational burden.
【2】 Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism
标题：基于音符位置感知注意机制的歌声合成
链接：https://arxiv.org/abs/2212.13703
*与cs.SD语音【5】为同一篇
作者：Yukiya Hono,Kei Hashimoto,Yoshihiko Nankaku,Keiichi Tokuda备注：5 pages, 4 figures, 2 tables, submitted to ICASSP 2023摘要：提出了一种新的具有音符位置感知注意机制的序列到序列（seq 2seq）模型用于歌声合成（SVS）。能够同时执行声学和时间建模的seq 2seq建模方法是有吸引力的。然而，由于歌唱声音的时间建模的困难，许多具有基于编码器-解码器的模型的最近SVS系统仍然显式地依赖于由附加模块生成的持续时间信息。虽然一些研究使用具有注意机制的seq 2seq模型执行同时建模，但是它们对于时间建模的鲁棒性不足。所提出的注意力机制被设计为通过考虑乐谱所给出的节奏来估计注意力权重。此外，还介绍了几种技术来提高歌声的建模性能。实验结果表明，该模型在定时的自然度和鲁棒性方面都是有效的。摘要：This paper proposes a novel sequence-to-sequence (seq2seq) model with a musical note position-aware attention mechanism for singing voice synthesis (SVS). A seq2seq modeling approach that can simultaneously perform acoustic and temporal modeling is attractive. However, due to the difficulty of the temporal modeling of singing voices, many recent SVS systems with an encoder-decoder-based model still rely on explicitly on duration information generated by additional modules. Although some studies perform simultaneous modeling using seq2seq models with an attention mechanism, they have insufficient robustness against temporal modeling. The proposed attention mechanism is designed to estimate the attention weights by considering the rhythm given by the musical score. Furthermore, several techniques are also introduced to improve the modeling performance of the singing voice. Experimental results indicated that the proposed model is effective in terms of both naturalness and robustness of timing.
【3】 Audiovisual Database with 360 Video and Higher-Order Ambisonics Audio for Perception, Cognition, Behavior, and QoE Evaluation Research
标题：360视频视听数据库和高阶两用音响对感知、认知、行为和QOE评价的研究
链接：https://arxiv.org/abs/2212.13442
*与cs.SD语音【6】为同一篇
作者：Thomas Robotham,Ashutosh Singla,Olli S. Rummukainen,Alexander Raake,Emanuël A. P. Habets备注：6 pages, 2 figures, accepted and presented at the 2022 14th International Conference on Quality of Multimedia Experience (QoMEX). Database is publicly accessible at this https URL摘要：对多模态感知、人类认知、行为和注意力的研究可以受益于高保真内容，当在头戴式显示器上呈现时，高保真内容可以再现类似真实生活的场景。此外，视听感知、认知过程和行为等方面可以补充基于问卷的交互式虚拟环境体验质量（QoE）评估。当前，缺乏可用于评估能够再现高质量内容的这些方面或系统的高质量开源视听数据库。通过本文，我们提供了一个公开的视听数据库，其中包含12个捕捉真实自然和城市环境的场景，视频分辨率为7680 x3840，每秒60帧，并带有4阶Ambisonics音频。这360个视频序列，平均持续时间为60秒，代表了用于系统评估单/多模态感知、认知、行为和QoE的各个维度的现实生活设置。本文详细介绍了场景要求、录制方法和场景描述。该数据库提供了高质量的参考材料，平衡地侧重于听觉和视觉感官信息。该数据库将不断更新，增加场景和其他元数据，如人的评分和显著性信息。摘要：Research into multi-modal perception, human cognition, behavior, and attention can benefit from high-fidelity content that may recreate real-life-like scenes when rendered on head-mounted displays. Moreover, aspects of audiovisual perception, cognitive processes, and behavior may complement questionnaire-based Quality of Experience (QoE) evaluation of interactive virtual environments. Currently, there is a lack of high-quality open-source audiovisual databases that can be used to evaluate such aspects or systems capable of reproducing high-quality content. With this paper, we provide a publicly available audiovisual database consisting of twelve scenes capturing real-life nature and urban environments with a video resolution of 7680x3840 at 60 frames-per-second and with 4th-order Ambisonics audio. These 360 video sequences, with an average duration of 60 seconds, represent real-life settings for systematically evaluating various dimensions of uni-/multi-modal perception, cognition, behavior, and QoE. The paper provides details of the scene requirements, recording approach, and scene descriptions. The database provides high-quality reference material with a balanced focus on auditory and visual sensory information. The database will be continuously updated with additional scenes and further metadata such as human ratings and saliency information.
【4】 Voice conversion with limited data and limitless data augmentations
标题：有限数据和无限数据扩充的语音转换
链接：https://arxiv.org/abs/2212.13581
*与cs.SD语音【2】为同一篇
作者：Olga Slizovskaia,Jordi Janer,Pritish Chandna,Oscar Mayor摘要：对输入语音信号施加改变以将感知的语音说话者改变为目标，同时保持输入的内容是一项具有挑战性但有趣的任务，称为话音转换（VC）。在过去的几年中，这项任务已经获得了极大的兴趣，其中大多数系统使用数据驱动的机器学习模型。在低延迟的真实场景中进行转换更具有挑战性，因为高质量数据的可用性受到限制。诸如音调移位和噪声添加之类的数据扩充经常用于增加用于训练该任务的基于机器学习的模型的数据量。在本文中，我们探讨了用于实时语音转换的常见数据增强技术的功效，并介绍了基于音频和语音变换效果的数据增强新技术。我们使用客观和主观的评价方法来评价男性和女性目标说话人的转换。摘要：Applying changes to an input speech signal to change the perceived speaker of speech to a target while maintaining the content of the input is a challenging but interesting task known as Voice conversion (VC). Over the last few years, this task has gained significant interest where most systems use data-driven machine learning models. Doing the conversion in a low-latency real-world scenario is even more challenging constrained by the availability of high-quality data. Data augmentations such as pitch shifting and noise addition are often used to increase the amount of data used for training machine learning based models for this task. In this paper we explore the efficacy of common data augmentation techniques for real-time voice conversion and introduce novel techniques for data augmentation based on audio and voice transformation effects as well. We evaluate the conversions for both male and female target speakers using objective and subjective evaluation methodologies.
【5】 Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation
标题：不要太过于自信!利用置信度松弛提高ASR译码性能
链接：https://arxiv.org/abs/2212.13378
*与cs.SD语音【3】为同一篇
作者：Tomer Wullach,Shlomo E. Chazan摘要：自动语音识别（ASR）系统经常使用基于搜索的解码策略，旨在通过考虑多个候选来找到最佳可获得的抄本。一个突出的语音识别解码试探法是波束搜索，其寻找具有使用预测分布计算的最大似然性的抄本。虽然在各种任务中表现出实质性的性能增益，但是当预测概率高度可信时，即，预测的分布集中在单个或非常少的类别。我们表明，最近提出的自我监督学习（SSL）为基础的ASR模型往往产生异常自信的预测，可能会阻碍波束搜索从真正考虑一个多样化的候选集。我们执行一个层次分析来揭示和可视化预测如何演变，并提出一个解码过程，提高了微调ASR模型的性能。我们提出的方法不需要超出原始微调的进一步训练，也不需要额外的模型参数。事实上，我们发现我们所提出的方法比现有方法需要更少的推理计算。我们建议聚合前M层，潜在地利用中间层中编码的有用信息，并放松模型置信度。我们通过对不同数量的标记资源和不同的模型大小进行实证研究来证明我们的方法的有效性，特别是当应用于低资源场景时，显示出一致的改进。摘要：Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search, which seeks the transcript with the greatest likelihood computed using the predicted distribution. While showing substantial performance gains in various tasks, beam search loses some of its effectiveness when the predicted probabilities are highly confident, i.e., the predicted distribution is massed for a single or very few classes. We show that recently proposed Self-Supervised Learning (SSL)-based ASR models tend to yield exceptionally confident predictions that may hamper beam search from truly considering a diverse set of candidates. We perform a layer analysis to reveal and visualize how predictions evolve, and propose a decoding procedure that improves the performance of fine-tuned ASR models. Our proposed approach does not require further training beyond the original fine-tuning, nor additional model parameters. In fact, we find that our proposed method requires significantly less inference computation than current approaches. We propose aggregating the top M layers, potentially leveraging useful information encoded in intermediate layers, and relaxing model confidence. We demonstrate the effectiveness of our approach by conducting an empirical study on varying amounts of labeled resources and different model sizes, showing consistent improvements in particular when applied to low-resource scenarios.
【6】 Feature Selection Approaches for Optimising Music Emotion Recognition Methods
标题：优化音乐情感识别方法的特征选择方法
链接：https://arxiv.org/abs/2212.13369
*与cs.SD语音【4】为同一篇
作者：Le Cai,Sam Ferguson,Haiyan Lu,Gengfa Fang摘要：特征的高维度是音乐情感识别的一个挑战。关于音频特征和情感之间的关系没有共同的共识。MER系统使用所有可用的特征来识别情感;然而，由于其包含充当噪声的不相关数据，因此这不是最佳解决方案。本文提出了一种特征选择方法来消除多目标匹配中的冗余特征。我们基于特征选择算法（FSA）创建了一个选定特征集（SFS），并通过使用两个模型（支持向量回归（SVR）和随机森林（RF））进行训练，并将其与使用完整特征集（CFS）进行比较来对其进行基准测试。实验结果表明，SFS的引入提高了随机森林（RF）和支持向量回归（SVR）模型的MER性能。我们发现使用FSA可以在所有场景下提高性能，并且它对MER任务的模型效率和稳定性具有潜在的好处。摘要：The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion; however, this is not an optimal solution since it contains irrelevant data acting as noise. In this paper, we introduce a feature selection approach to eliminate redundant features for MER. We created a Selected Feature Set (SFS) based on the feature selection algorithm (FSA) and benchmarked it by training with two models, Support Vector Regression (SVR) and Random Forest (RF) and comparing them against with using the Complete Feature Set (CFS). The result indicates that the performance of MER has improved for both Random Forest (RF) and Support Vector Regression (SVR) models by using SFS. We found using FSA can improve performance in all scenarios, and it has potential benefits for model efficiency and stability for MER task.机器翻译，仅供参考
每日语音速递