今日论文合集：cs.SD语音5篇，eess.AS音频处理6篇。
cs.SD语音
【1】 Adversarial Training of Denoising Diffusion Model Using Dual  Discriminators for High-Fidelity Multi-Speaker TTS标题：高保真多说话人TTS双区分器去噪扩散模型对抗训练链接：https://arxiv.org/abs/2308.01573
作者：Myeongjin Ko,Yong-Hoon Choi机构：School of Robotics, Kwangwoon University, Seoul , South Korea, This work was supported in part by the National Research Foundation of Korea (NRF) Grant funded by the Korea Government MSIT under Grant, R,F,A,.摘要：扩散模型能够通过概率方法生成高质量的数据。然而，由于需要大量的时间步长，它具有生成速度慢的缺点。为了解决这一限制，最近的模型，如去噪扩散隐式模型（DDIM），专注于生成样本，而不直接建模概率分布，而像去噪扩散生成对抗网络（GAN）这样的模型将扩散过程与GANs相结合。在语音合成领域，最近的扩散语音合成模型称为DiffGAN-TTS，利用GANs的结构，已经被引入，并在语音质量和生成速度方面表现出优异的性能。在本文中，为了进一步提高DiffGAN-TTS的性能，我们提出了一种具有两个鉴别器的语音合成模型：用于学习逆过程的分布的扩散鉴别器和用于学习生成的数据的分布的谱图鉴别器。客观指标，如结构相似性指数测度（SSIM），梅尔倒谱失真（MCD），F0均方根误差（F0 RMSE），短时客观清晰度（STOI），语音质量的感知评价（PESQ），以及主观指标，如平均意见得分（MOS），被用来评估所提出的模型的性能。评估结果表明，该模型优于最近的国家的最先进的模型，如FastSpeech 2和DiffGAN-TTS在各种指标。我们的实现和音频示例位于GitHub上。摘要：The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this limitation, recent models such as denoising diffusion implicit models (DDIM) focus on generating samples without directly modeling the probability distribution, while models like denoising diffusion generative adversarial networks (GAN) combine diffusion processes with GANs. In the field of speech synthesis, a recent diffusion speech synthesis model called DiffGAN-TTS, utilizing the structure of GANs, has been introduced and demonstrates superior performance in both speech quality and generation speed. In this paper, to further enhance the performance of DiffGAN-TTS, we propose a speech synthesis model with two discriminators: a diffusion discriminator for learning the distribution of the reverse process and a spectrogram discriminator for learning the distribution of the generated data. Objective metrics such as structural similarity index measure (SSIM), mel-cepstral distortion (MCD), F0 root mean squared error (F0 RMSE), short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ), as well as subjective metrics like mean opinion score (MOS), are used to evaluate the performance of the proposed model. The evaluation results show that the proposed model outperforms recent state-of-the-art models such as FastSpeech2 and DiffGAN-TTS in various metrics. Our implementation and audio samples are located on GitHub.
【2】 MusicLDM: Enhancing Novelty in Text-to-Music Generation Using  Beat-Synchronous Mixup Strategies标题：MusicLDM：使用节拍同步混合策略增强文本到音乐生成的新颖性链接：https://arxiv.org/abs/2308.01546
作者：Ke Chen,Yusong Wu,Haohe Liu,Marianna Nezhurina,Taylor Berg-Kirkpatrick,Shlomo Dubnov机构：University of California San Diego, Mila, Quebec Artificial Intelligence Institute, Université de Montréal, Centre for Vision Speech and Signal Processing, University of Surrey, LAION备注：16 pages, 3 figures, 2 tables, demo page: this https URL摘要：扩散模型已经在跨模态生成任务中显示出有希望的结果，包括文本到图像和文本到音频生成。然而，生成音乐作为一种特殊类型的音频，由于音乐数据的有限可用性以及与版权和剽窃相关的敏感问题而呈现出独特的挑战。在本文中，为了解决这些挑战，我们首先构建了一个国家的最先进的文本到音乐模型，MusicLDM，适应稳定扩散和AudioLDM架构的音乐领域。我们实现了这一目标，通过重新训练的对比语言音频预训练模型（CLAP）和Hifi-GAN声码器，作为MusicLDM的组成部分，在音乐数据样本的集合。然后，为了解决训练数据的局限性并避免剽窃，我们利用节拍跟踪模型并提出了两种不同的数据增强混合策略：节拍同步音频混合和节拍同步潜在混合，它们分别直接或经由潜在嵌入空间重新组合训练音频。这种混合策略鼓励模型在音乐训练样本之间进行插值，并在训练数据的凸包内生成新的音乐，使生成的音乐更加多样化，同时仍然忠实于相应的风格。除了流行的评价指标，我们设计了几个新的评价指标的基础上CLAP得分证明，我们提出的MusicLDM和节拍同步混合策略，提高了质量和新颖性的生成的音乐，以及输入文本和生成的音乐之间的对应关系。摘要：Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited availability of music data and sensitive issues related to copyright and plagiarism. In this paper, to tackle these challenges, we first construct a state-of-the-art text-to-music model, MusicLDM, that adapts Stable Diffusion and AudioLDM architectures to the music domain. We achieve this by retraining the contrastive language-audio pretraining model (CLAP) and the Hifi-GAN vocoder, as components of MusicLDM, on a collection of music data samples. Then, to address the limitations of training data and to avoid plagiarism, we leverage a beat tracking model and propose two different mixup strategies for data augmentation: beat-synchronous audio mixup and beat-synchronous latent mixup, which recombine training audio directly or via a latent embeddings space, respectively. Such mixup strategies encourage the model to interpolate between musical training samples and generate new music within the convex hull of the training data, making the generated music more diverse while still staying faithful to the corresponding style. In addition to popular evaluation metrics, we design several new evaluation metrics based on CLAP score to demonstrate that our proposed MusicLDM and beat-synchronous mixup strategies improve both the quality and novelty of generated music, as well as the correspondence between input text and generated music.
【3】 Optimizing multi-user sound communications in reverberating environments  with acoustic reconfigurable metasurfaces标题：利用声学可重构元表面优化混响环境中的多用户声音通信链接：https://arxiv.org/abs/2308.01531
作者：Hongkuan Zhang,Qiyuan Wang,Mathias Fink,Guancong Ma机构：Department of Physics, Hong Kong Baptist University, Kowloon Tong, Hong Kong, Institut Langevin, ESPCI Paris, Université PSL, CNRS, Paris, France摘要：如何确保在混响室中，几个人可以同时对其他几个人说话，使他们完全理解自己，并且在消息之间没有任何串扰？在这项工作中，我们报告了一个概念性的解决方案，这个问题，通过开发一个智能声学墙，它可以重新配置电子和学习算法，适应房间的几何形状和源和接收器的位置控制。为此，房间边界的一部分覆盖有由宽带声学可重构元表面（ARM）制成的智能镜，该智能镜被设计成通过200个独立可调谐单元在反射波中提供两态（0或{\pi}）相移。整个相位图案被优化以最大化香农容量，同时最小化不同源和接收器之间的串扰。我们展示了多光谱声场的控制，覆盖的频谱远大于房间的相干带宽，用于各种引人注目的功能，包括无串扰的声学通信，频率复用通信和多用户通信。针对两个不同的人用两个音乐源进行的实验展示了无串扰的同时音乐回放。我们的工作为复杂介质中的声波控制和新一代声学设备开辟了新的途径。摘要：How do you ensure that, in a reverberant room, several people can speak simultaneously to several other people, making themselves perfectly understood and without any crosstalk between messages? In this work, we report a conceptual solution to this problem by developing an intelligent acoustic wall, which can be reconfigured electronically and is controlled by a learning algorithm that adapts to the geometry of the room and the positions of sources and receivers. To this end, a portion of the room boundaries is covered with a smart mirror made of a broadband acoustic reconfigurable metasurface (ARMs) designed to provide a two-state (0 or {\pi}) phase shift in the reflected waves by 200 independently tunable units. The whole phase pattern is optimized to maximize the Shannon capacity while minimizing crosstalk between the different sources and receivers. We demonstrate the control of multi-spectral sound fields covering a spectrum much larger than the coherence bandwidth of the room for diverse striking functionalities, including crosstalk-free acoustic communication, frequency-multiplexed communications, and multi-user communications. An experiment conducted with two music sources for two different people demonstrates a crosstalk-free simultaneous music playback. Our work opens new routes for the control of sound waves in complex media and for a new generation of acoustic devices.
【4】 Careful Whisper -- leveraging advances in automatic speech recognition  for robust and interpretable aphasia subtype classification标题：小心的耳语--利用自动语音识别的进步，实现健壮和可解释的失语症亚型分类链接：https://arxiv.org/abs/2308.01327
作者：Laurin Wagner,Mario Zusag,Theresa Bloder机构：nyra health GmbH, Austria摘要：本文提出了一种完全自动化的方法来识别语音异常的录音，以帮助评估言语障碍。通过结合连接主义时间分类（CTC）和基于编码器-解码器的自动语音识别模型，我们生成丰富的声学和干净的成绩单。然后，我们应用几种自然语言处理方法从这些成绩单中提取特征，以产生健康语音的原型。来自这些原型的基本距离测量作为标准机器学习分类器的输入特征，从而在失语症患者和健康对照组的记录之间产生人类水平的准确性。此外，最常发生的失语症类型可以区分90%的准确率。该管道直接适用于其他疾病和语言，显示出稳健提取诊断语音生物标志物的前景。摘要：This paper presents a fully automated approach for identifying speech anomalies from voice recordings to aid in the assessment of speech impairments. By combining Connectionist Temporal Classification (CTC) and encoder-decoder-based automatic speech recognition models, we generate rich acoustic and clean transcripts. We then apply several natural language processing methods to extract features from these transcripts to produce prototypes of healthy speech. Basic distance measures from these prototypes serve as input features for standard machine learning classifiers, yielding human-level accuracy for the distinction between recordings of people with aphasia and a healthy control group. Furthermore, the most frequently occurring aphasia types can be distinguished with 90% accuracy. The pipeline is directly applicable to other diseases and languages, showing promise for robustly extracting diagnostic speech biomarkers.
【5】 Versatile Time-Frequency Representations Realized by Convex Penalty on  Magnitude Spectrogram标题：用幅度谱图的凸罚实现通用的时频表示链接：https://arxiv.org/abs/2308.01665
作者：Keidai Arai,Koki Yamada,Kohei Yatabe机构：)The authors are with Tokyo University of Agriculture and Technol-ogy备注：5 pages, 3 figures摘要：稀疏时频（T-F）表示是近几十年来的一个重要研究课题。其中，基于优化的方法（特别是基追踪的扩展）允许我们通过目标函数来设计表示。由于声学信号处理利用频谱图的模型，因此基于优化的T-F表示的灵活性有助于针对每个应用调整表示。然而，声学应用通常需要通过离散Gabor变换（DGT）获得的T-F表示的\textit{幅度}的模型。将T-F表示调整到这样的幅度模型（例如，DGT系数的大小的平滑度）导致难以求解的非凸优化问题。在本文中，而不是解决困难的非凸问题，我们提出了一个基于凸优化的框架，实现了T-F表示，其幅度具有用户指定的特性。我们分析了所提出的方法的性质，并提供了稀疏T-F表示的数值例子，例如，低秩或平滑的幅度，这是以前没有实现的。摘要：Sparse time-frequency (T-F) representations have been an important research topic for more than several decades. Among them, optimization-based methods (in particular, extensions of basis pursuit) allow us to design the representations through objective functions. Since acoustic signal processing utilizes models of spectrogram, the flexibility of optimization-based T-F representations is helpful for adjusting the representation for each application. However, acoustic applications often require models of \textit{magnitude} of T-F representations obtained by discrete Gabor transform (DGT). Adjusting a T-F representation to such a magnitude model (e.g., smoothness of magnitude of DGT coefficients) results in a non-convex optimization problem that is difficult to solve. In this paper, instead of tackling difficult non-convex problems, we propose a convex optimization-based framework that realizes a T-F representation whose magnitude has characteristics specified by the user. We analyzed the properties of the proposed method and provide numerical examples of sparse T-F representations having, e.g., low-rank or smooth magnitude, which have not been realized before.
eess.AS音频处理
【1】 Versatile Time-Frequency Representations Realized by Convex Penalty on  Magnitude Spectrogram标题：用幅度谱图的凸罚实现通用的时频表示链接：https://arxiv.org/abs/2308.01665
作者：Keidai Arai,Koki Yamada,Kohei Yatabe机构：)The authors are with Tokyo University of Agriculture and Technol-ogy备注：5 pages, 3 figures摘要：稀疏时频（T-F）表示是近几十年来的一个重要研究课题。其中，基于优化的方法（特别是基追踪的扩展）允许我们通过目标函数来设计表示。由于声学信号处理利用频谱图的模型，因此基于优化的T-F表示的灵活性有助于针对每个应用调整表示。然而，声学应用通常需要通过离散Gabor变换（DGT）获得的T-F表示的\textit{幅度}的模型。将T-F表示调整到这样的幅度模型（例如，DGT系数的大小的平滑度）导致难以求解的非凸优化问题。在本文中，而不是解决困难的非凸问题，我们提出了一个基于凸优化的框架，实现了T-F表示，其幅度具有用户指定的特性。我们分析了所提出的方法的性质，并提供了稀疏T-F表示的数值例子，例如，低秩或平滑的幅度，这是以前没有实现的。摘要：Sparse time-frequency (T-F) representations have been an important research topic for more than several decades. Among them, optimization-based methods (in particular, extensions of basis pursuit) allow us to design the representations through objective functions. Since acoustic signal processing utilizes models of spectrogram, the flexibility of optimization-based T-F representations is helpful for adjusting the representation for each application. However, acoustic applications often require models of \textit{magnitude} of T-F representations obtained by discrete Gabor transform (DGT). Adjusting a T-F representation to such a magnitude model (e.g., smoothness of magnitude of DGT coefficients) results in a non-convex optimization problem that is difficult to solve. In this paper, instead of tackling difficult non-convex problems, we propose a convex optimization-based framework that realizes a T-F representation whose magnitude has characteristics specified by the user. We analyzed the properties of the proposed method and provide numerical examples of sparse T-F representations having, e.g., low-rank or smooth magnitude, which have not been realized before.
【2】 Many-to-Many Spoken Language Translation via Unified Speech and Text  Representation Learning with Unit-to-Unit Translation标题：基于统一语音和文本表示的多对多口语翻译链接：https://arxiv.org/abs/2308.01831
作者：Minsu Kim,Jeongsoo Choi,Dahun Kim,Yong Man Ro机构：Image and Video Systems Lab, KAIST, Google DeepMind摘要：在本文中，我们提出了一种方法来学习统一表示的多语种语音和文本与一个单一的模型，特别是专注于语音合成的目的。我们表示多语言语音音频与语音单元，量化表示的语音特征编码的自监督语音模型。因此，我们可以通过将音频视为伪文本来关注它们的语言内容，并且可以建立语音和文本的统一表示。然后，我们建议在多语言数据上训练具有单元到单元翻译（UTUT）目标的编码器-解码器结构化模型。具体地，通过用源语言标记调节编码器并且用目标语言标记调节解码器，在多对多语言翻译设置中，优化模型以将口语翻译成目标语言的口语。因此，该模型可以构建如何理解口语以及如何将它们与不同语言相关联的知识。具有UTUT的单个预训练模型可用于各种多语言语音和文本相关任务，例如语音到语音翻译（STS）、多语言文本到语音合成（TTS）和文本到语音翻译（TTST）。通过进行全面的实验，包括各种语言，我们验证了所提出的方法在不同的多语言任务的有效性。此外，我们表明UTUT可以执行多对多语言STS，这是以前没有在文献中探索。样品可在https://choijeongsoo.github.io/utut上获得。摘要：In this paper, we propose a method to learn unified representations of multilingual speech and text with a single model, especially focusing on the purpose of speech synthesis. We represent multilingual speech audio with speech units, the quantized representations of speech features encoded from a self-supervised speech model. Therefore, we can focus on their linguistic content by treating the audio as pseudo text and can build a unified representation of speech and text. Then, we propose to train an encoder-decoder structured model with a Unit-to-Unit Translation (UTUT) objective on multilingual data. Specifically, by conditioning the encoder with the source language token and the decoder with the target language token, the model is optimized to translate the spoken language into that of the target language, in a many-to-many language translation setting. Therefore, the model can build the knowledge of how spoken languages are comprehended and how to relate them to different languages. A single pre-trained model with UTUT can be employed for diverse multilingual speech- and text-related tasks, such as Speech-to-Speech Translation (STS), multilingual Text-to-Speech Synthesis (TTS), and Text-to-Speech Translation (TTST). By conducting comprehensive experiments encompassing various languages, we validate the efficacy of the proposed method across diverse multilingual tasks. Moreover, we show UTUT can perform many-to-many language STS, which has not been previously explored in the literature. Samples are available on https://choijeongsoo.github.io/utut.
【3】 Adversarial Training of Denoising Diffusion Model Using Dual  Discriminators for High-Fidelity Multi-Speaker TTS标题：高保真多说话人TTS双区分器去噪扩散模型对抗训练链接：https://arxiv.org/abs/2308.01573
作者：Myeongjin Ko,Yong-Hoon Choi机构：School of Robotics, Kwangwoon University, Seoul , South Korea, This work was supported in part by the National Research Foundation of Korea (NRF) Grant funded by the Korea Government MSIT under Grant, R,F,A,.摘要：扩散模型能够通过概率方法生成高质量的数据。然而，由于需要大量的时间步长，它具有生成速度慢的缺点。为了解决这一限制，最近的模型，如去噪扩散隐式模型（DDIM），专注于生成样本，而不直接建模概率分布，而像去噪扩散生成对抗网络（GAN）这样的模型将扩散过程与GANs相结合。在语音合成领域，最近的扩散语音合成模型称为DiffGAN-TTS，利用GANs的结构，已经被引入，并在语音质量和生成速度方面表现出优异的性能。在本文中，为了进一步提高DiffGAN-TTS的性能，我们提出了一种具有两个鉴别器的语音合成模型：用于学习逆过程的分布的扩散鉴别器和用于学习生成的数据的分布的谱图鉴别器。客观指标，如结构相似性指数测度（SSIM），梅尔倒谱失真（MCD），F0均方根误差（F0 RMSE），短时客观清晰度（STOI），语音质量的感知评价（PESQ），以及主观指标，如平均意见得分（MOS），被用来评估所提出的模型的性能。评估结果表明，该模型优于最近的国家的最先进的模型，如FastSpeech 2和DiffGAN-TTS在各种指标。我们的实现和音频示例位于GitHub上。摘要：The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this limitation, recent models such as denoising diffusion implicit models (DDIM) focus on generating samples without directly modeling the probability distribution, while models like denoising diffusion generative adversarial networks (GAN) combine diffusion processes with GANs. In the field of speech synthesis, a recent diffusion speech synthesis model called DiffGAN-TTS, utilizing the structure of GANs, has been introduced and demonstrates superior performance in both speech quality and generation speed. In this paper, to further enhance the performance of DiffGAN-TTS, we propose a speech synthesis model with two discriminators: a diffusion discriminator for learning the distribution of the reverse process and a spectrogram discriminator for learning the distribution of the generated data. Objective metrics such as structural similarity index measure (SSIM), mel-cepstral distortion (MCD), F0 root mean squared error (F0 RMSE), short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ), as well as subjective metrics like mean opinion score (MOS), are used to evaluate the performance of the proposed model. The evaluation results show that the proposed model outperforms recent state-of-the-art models such as FastSpeech2 and DiffGAN-TTS in various metrics. Our implementation and audio samples are located on GitHub.
【4】 MusicLDM: Enhancing Novelty in Text-to-Music Generation Using  Beat-Synchronous Mixup Strategies标题：MusicLDM：使用节拍同步混合策略增强文本到音乐生成的新颖性链接：https://arxiv.org/abs/2308.01546
作者：Ke Chen,Yusong Wu,Haohe Liu,Marianna Nezhurina,Taylor Berg-Kirkpatrick,Shlomo Dubnov机构：University of California San Diego, Mila, Quebec Artificial Intelligence Institute, Université de Montréal, Centre for Vision Speech and Signal Processing, University of Surrey, LAION备注：16 pages, 3 figures, 2 tables, demo page: this https URL摘要：扩散模型已经在跨模态生成任务中显示出有希望的结果，包括文本到图像和文本到音频生成。然而，生成音乐作为一种特殊类型的音频，由于音乐数据的有限可用性以及与版权和剽窃相关的敏感问题而呈现出独特的挑战。在本文中，为了解决这些挑战，我们首先构建了一个国家的最先进的文本到音乐模型，MusicLDM，适应稳定扩散和AudioLDM架构的音乐领域。我们实现了这一目标，通过重新训练的对比语言音频预训练模型（CLAP）和Hifi-GAN声码器，作为MusicLDM的组成部分，在音乐数据样本的集合。然后，为了解决训练数据的局限性并避免剽窃，我们利用节拍跟踪模型并提出了两种不同的数据增强混合策略：节拍同步音频混合和节拍同步潜在混合，它们分别直接或经由潜在嵌入空间重新组合训练音频。这种混合策略鼓励模型在音乐训练样本之间进行插值，并在训练数据的凸包内生成新的音乐，使生成的音乐更加多样化，同时仍然忠实于相应的风格。除了流行的评价指标，我们设计了几个新的评价指标的基础上CLAP得分证明，我们提出的MusicLDM和节拍同步混合策略，提高了质量和新颖性的生成的音乐，以及输入文本和生成的音乐之间的对应关系。摘要：Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited availability of music data and sensitive issues related to copyright and plagiarism. In this paper, to tackle these challenges, we first construct a state-of-the-art text-to-music model, MusicLDM, that adapts Stable Diffusion and AudioLDM architectures to the music domain. We achieve this by retraining the contrastive language-audio pretraining model (CLAP) and the Hifi-GAN vocoder, as components of MusicLDM, on a collection of music data samples. Then, to address the limitations of training data and to avoid plagiarism, we leverage a beat tracking model and propose two different mixup strategies for data augmentation: beat-synchronous audio mixup and beat-synchronous latent mixup, which recombine training audio directly or via a latent embeddings space, respectively. Such mixup strategies encourage the model to interpolate between musical training samples and generate new music within the convex hull of the training data, making the generated music more diverse while still staying faithful to the corresponding style. In addition to popular evaluation metrics, we design several new evaluation metrics based on CLAP score to demonstrate that our proposed MusicLDM and beat-synchronous mixup strategies improve both the quality and novelty of generated music, as well as the correspondence between input text and generated music.
【5】 Optimizing multi-user sound communications in reverberating environments  with acoustic reconfigurable metasurfaces标题：利用声学可重构元表面优化混响环境中的多用户声音通信链接：https://arxiv.org/abs/2308.01531
作者：Hongkuan Zhang,Qiyuan Wang,Mathias Fink,Guancong Ma机构：Department of Physics, Hong Kong Baptist University, Kowloon Tong, Hong Kong, Institut Langevin, ESPCI Paris, Université PSL, CNRS, Paris, France摘要：如何确保在混响室中，几个人可以同时对其他几个人说话，使他们完全理解自己，并且在消息之间没有任何串扰？在这项工作中，我们报告了一个概念性的解决方案，这个问题，通过开发一个智能声学墙，它可以重新配置电子和学习算法，适应房间的几何形状和源和接收器的位置控制。为此，房间边界的一部分覆盖有由宽带声学可重构元表面（ARM）制成的智能镜，该智能镜被设计成通过200个独立可调谐单元在反射波中提供两态（0或{\pi}）相移。整个相位图案被优化以最大化香农容量，同时最小化不同源和接收器之间的串扰。我们展示了多光谱声场的控制，覆盖的频谱远大于房间的相干带宽，用于各种引人注目的功能，包括无串扰的声学通信，频率复用通信和多用户通信。针对两个不同的人用两个音乐源进行的实验展示了无串扰的同时音乐回放。我们的工作为复杂介质中的声波控制和新一代声学设备开辟了新的途径。摘要：How do you ensure that, in a reverberant room, several people can speak simultaneously to several other people, making themselves perfectly understood and without any crosstalk between messages? In this work, we report a conceptual solution to this problem by developing an intelligent acoustic wall, which can be reconfigured electronically and is controlled by a learning algorithm that adapts to the geometry of the room and the positions of sources and receivers. To this end, a portion of the room boundaries is covered with a smart mirror made of a broadband acoustic reconfigurable metasurface (ARMs) designed to provide a two-state (0 or {\pi}) phase shift in the reflected waves by 200 independently tunable units. The whole phase pattern is optimized to maximize the Shannon capacity while minimizing crosstalk between the different sources and receivers. We demonstrate the control of multi-spectral sound fields covering a spectrum much larger than the coherence bandwidth of the room for diverse striking functionalities, including crosstalk-free acoustic communication, frequency-multiplexed communications, and multi-user communications. An experiment conducted with two music sources for two different people demonstrates a crosstalk-free simultaneous music playback. Our work opens new routes for the control of sound waves in complex media and for a new generation of acoustic devices.
【6】 Careful Whisper -- leveraging advances in automatic speech recognition  for robust and interpretable aphasia subtype classification标题：小心的耳语--利用自动语音识别的进步，实现健壮和可解释的失语症亚型分类链接：https://arxiv.org/abs/2308.01327
作者：Laurin Wagner,Mario Zusag,Theresa Bloder机构：nyra health GmbH, Austria摘要：本文提出了一种完全自动化的方法来识别语音异常的录音，以帮助评估言语障碍。通过结合连接主义时间分类（CTC）和基于编码器-解码器的自动语音识别模型，我们生成丰富的声学和干净的成绩单。然后，我们应用几种自然语言处理方法从这些成绩单中提取特征，以产生健康语音的原型。来自这些原型的基本距离测量作为标准机器学习分类器的输入特征，从而在失语症患者和健康对照组的记录之间产生人类水平的准确性。此外，最常发生的失语症类型可以区分90%的准确率。该管道直接适用于其他疾病和语言，显示出稳健提取诊断语音生物标志物的前景。摘要：This paper presents a fully automated approach for identifying speech anomalies from voice recordings to aid in the assessment of speech impairments. By combining Connectionist Temporal Classification (CTC) and encoder-decoder-based automatic speech recognition models, we generate rich acoustic and clean transcripts. We then apply several natural language processing methods to extract features from these transcripts to produce prototypes of healthy speech. Basic distance measures from these prototypes serve as input features for standard machine learning classifiers, yielding human-level accuracy for the distinction between recordings of people with aphasia and a healthy control group. Furthermore, the most frequently occurring aphasia types can be distinguished with 90% accuracy. The pipeline is directly applicable to other diseases and languages, showing promise for robustly extracting diagnostic speech biomarkers.
机器翻译，仅供参考