While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human evaluation scores with machine learning models. However, they rely on supervised learning and thus suffer from high annotation costs and domain-shift problems. We propose SpeechLMScore, an unsupervised metric to evaluate generated speech using a speech-language model. SpeechLMScore computes the average log-probability of a speech signal by mapping it into discrete tokens and measures the average probability of generating the sequence of tokens. Therefore, it does not require human annotation and is a highly scalable framework. Evaluation results demonstrate that the proposed metric shows a promising correlation with human evaluation scores on different speech generation tasks including voice conversion, text-to-speech, and speech enhancement.

口头语言建模的最新工作表明，可以从原始音频中学习语言的可能性，而无需任何文本标签。该方法首先依赖于将音频转换为一系列离散单元（或伪文本），然后直接在此类伪文本上训练语言模型。这是必要的离散瓶颈，在语音信号的编码中可能引入不可逆转的错误，还是我们可以完全没有离散单位学习语言模型？在这项工作中，我们研究了离散和连续表示在口语建模中的作用。我们表明，离散化对于口语建模的良好结果确实至关重要。我们表明，离散化可以从连续功能中消除语言上无关的信息，从而有助于提高语言建模表演。在这项研究的基础上，我们培训了Hubert功能离散单元的语言模型，达到新的最先进的结果，导致了零资源语音挑战的词汇，句法和语义指标2021（轨道1-仅讲话）。

我们介绍Audiolm，这是具有长期一致性高质量音频产生的框架。 Audiolm将输入音频映射到一系列离散令牌，并将音频生成作为此表示空间中的语言建模任务。我们展示了现有的音频令牌如何在重建质量和长期结构之间提供不同的权衡，我们提出了一个混合代币化计划来实现这两个目标。也就是说，我们利用在音频中预先训练的蒙版语言模型的离散激活来捕获长期结构和神经音频编解码器产生的离散代码，以实现高质量的合成。通过培训大型原始音频波形，Audiolm学会了在简短的提示下产生自然和连贯的连续性。当接受演讲训练时，没有任何笔录或注释，Audiolm会在句法和语义上产生可行的语音连续性，同时还为看不见的说话者保持说话者身份和韵律。此外，我们演示了我们的方法如何通过产生连贯的钢琴音乐连续性来超越语音，尽管受过训练而没有任何象征性的音乐代表。

文本数据的语言模型（LMS）已经广泛研究了语言生成和其他下游任务的实用性。然而，纯粹在语音域中的语言建模仍然是一个相对未开发的主题，具有传统语音LMS，通常根据用于学习语言的分布方面的辅助文本LMS。对于英语语言，这些LMS将单词视为原子单位，这提出了语言域中语言建模的固有挑战。在本文中，我们提出了一种新的基于LSTM的生成语音LM，它受CBY模型的启发，并建立在包括音节和音素的语言单元上。这在数据集中的话语中提供了更好的声学一致性，而不是单个MelspectRoge框架或整个单词。使用有限的数据集，比当代生成型号规模小的数量级，我们的模型非常近似于潺潺声音。我们展示了培训与辅助文本LMS，多任务学习目标和辅助关节特征的影响。通过我们的实验，我们还强调了一些众所周知的，但在培训生成语音LMS中记录的挑战不良，包括这些模型培训的监督学习目标之间的不匹配，例如平均平方误差（MSE），以及真实目标是语音质量。我们的实验提供了早期迹象表明，验证损失和MCD）与生成的语音质量没有强烈相关，传统的文本语言建模度量，如困惑和下一个令牌预测准确性。

语音中的自我监督学习涉及在大规模的未注释的语音语料库上训练语音表示网络，然后将学习的表示形式应用于下游任务。由于语音中SSL学习的大多数下游任务主要集中在语音中的内容信息上，因此最理想的语音表示形式应该能够将不需要的变化（例如说话者的变化）从内容中删除。但是，解开扬声器非常具有挑战性，因为删除说话者的信息也很容易导致内容丢失，而后者的损害通常远远超过了前者的好处。在本文中，我们提出了一种新的SSL方法，该方法可以实现扬声器分解而不会严重丢失内容。我们的方法是根据休伯特框架改编的，并结合了解开机制，以使教师标签和博学的代表规范化。我们在一组与内容相关的下游任务上评估了说话者分解的好处，并观察到我们的扬声器示词表示的一致且著名的性能优势。

在这项工作中，我们介绍了SOMOS数据集，这是第一个大规模的意见分数（MOS）数据集，该数据集由完全神经文本到语音（TTS）样本组成。它可以用于训练专注于现代合成器评估的自动MOS预测系统，并可以刺激声学模型评估的进步。它由LJ语音语音的20k合成话语组成，LJ语音是一个公共领域的语音数据集，是建立神经声学模型和声码器的常见基准。来自200 TTS系统（包括香草神经声学模型以及允许韵律变化的模型）产生的话语。 LPCNET VOCODER用于所有系统，因此样品的变化仅取决于声学模型。合成的话语提供了平衡，足够的域和长度覆盖范围。我们对3个英国亚马逊机械土耳其人地点进行了MOS自然评估，并共享实践，从而为这项任务提供可靠的人群注释。我们为SOMOS数据集上的最先进的MOS预测模型提供了基线结果，并显示了该模型在评估TTS话语时所面临的局限性。

Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing. Traditional intrusive speech quality assessment requires the clean reference of the degraded utterance to provide an accurate quality measurement. This requirement limits the usability of these methods in real-world scenarios. On the other hand, non-intrusive subjective measurement is the ``golden standard" in evaluating speech quality as human listeners can intrinsically evaluate the quality of any degraded speech with ease. In this paper, we propose a novel end-to-end model structure called Convolutional Context-Aware Transformer (CCAT) network to predict the mean opinion score (MOS) of human raters. We evaluate our model on three MOS-annotated datasets spanning multiple languages and distortion types and submit our results to the ConferencingSpeech 2022 Challenge. Our experiments show that CCAT provides promising MOS predictions compared to current state-of-art non-intrusive speech assessment models with average Pearson correlation coefficient (PCC) increasing from 0.530 to 0.697 and average RMSE decreasing from 0.768 to 0.570 compared to the baseline model on the challenge evaluation test set.

语音情感转换是修改语音话语的感知情绪的任务，同时保留词汇内容和扬声器身份。在这项研究中，我们将情感转换问题作为口语翻译任务。我们将演讲分解为离散和解散的学习表现，包括内容单位，F0，扬声器和情感。首先，我们通过将内容单元转换为目标情绪来修改语音内容，然后基于这些单元预测韵律特征。最后，通过将预测的表示馈送到神经声码器中来生成语音波形。这样的范式允许我们超越信号的光谱和参数变化，以及模型非口头发声，例如笑声插入，打开拆除等。我们客观地和主观地展示所提出的方法在基础上优于基线感知情绪和音频质量。我们严格评估了这种复杂系统的所有组成部分，并通过广泛的模型分析和消融研究结束，以更好地强调建议方法的建筑选择，优势和弱点。示例和代码将在以下链接下公开使用：https://speechbot.github.io/emotion。

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in Automatic Speech Recognition (ASR) and speaker verification tasks respectively. However, it is still an open challenging research question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for unsupervised training schemes to achieve robust large-scale and speaker-independent ASR. The aim of this paper is to address the disentanglement of emotional prosody from speech based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed speech reconstruction model Prosody2Vec: (1) a unit encoder that transforms speech signals into discrete units for semantic content, (2) a pretrained speaker verification model to generate speaker identity embeddings, and (3) a trainable prosody encoder to learn prosody representations. We first pretrain the Prosody2Vec representations on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks. Both objective and subjective evaluations on the EVC task suggest that Prosody2Vec effectively captures general prosodic features that can be smoothly transferred to other emotional speech. In addition, our SER experiments on the IEMOCAP dataset reveal that the prosody features learned by Prosody2Vec are complementary and beneficial for the performance of widely used speech pretraining models and surpass the state-of-the-art methods when combining Prosody2Vec with HuBERT representations. Some audio samples can be found on our demo website.

Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, {\textit UnitY}, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However, predicting discrete units achieves 2.51x decoding speed-up compared to that case.

在这项研究中，我们提出了一种跨域多目标语音评估模型，即MOSA-net，可以同时估算多个语音评估度量。更具体地，MOSA-Net旨在基于作为输入的测试语音信号来估计语音质量，可懂度和失真评估分数。它包括用于表示提取的卷积神经网络和双向长短期存储器（CNN-BLSTM）架构，以及每个评估度量的乘法注意层和完全连接的层。此外，来自自我监督学习模型的跨域特征（光谱和时域特征）和潜在的表示用作将丰富的声学信息与不同语音表示相结合的输入，以获得更准确的评估。实验结果表明，MOSA-Net可以精确地预测语音质量（PESQ），短时间客观可懂度（STOI）和语音失真指数（SDI）分数的感知评估，并且在噪声下进行了测试，并且在任何看法测试下都有增强的语音话语条件（测试扬声器和训练集中涉及的噪音类型）或看不见的测试条件（其中测试扬声器和噪声类型不参与训练集）。鉴于确认的预测能力，我们进一步采用了MOSA网的潜在表示来引导语音增强（SE）过程，并导出了质量清晰度（QI）-AWARE SE（QIA-SE）方法。实验结果表明，与客观评估指标和定性评估测试相比，QIA-SE与基线SE系统相比提供了卓越的增强性能。

情绪转换（EVC）寻求转换话语的情绪状态，同时保留语言内容和扬声器身份。在EVC，情绪通常被视为离散类别，忽略了言论也传达了听众可以感知的各种强度水平的情绪。在本文中，我们的目标是明确地表征和控制情绪强度。我们建议解开语言内容的扬声器风格，并将扬声器风格编码成一个嵌入的嵌入空间，形成情绪嵌入的原型。我们进一步从情感标记的数据库中了解实际的情感编码器，并研究使用相对属性来表示细粒度的情绪强度。为确保情绪可理解性，我们将情感分类损失和情感嵌入了EVC网络培训中的相似性损失。根据需要，所提出的网络控制输出语音中的细粒度情绪强度。通过目标和主观评估，我们验证了建议网络的情感表达和情感强度控制的有效性。

In this paper, we present a novel method for phoneme-level prosody control of F0 and duration using intuitive discrete labels. We propose an unsupervised prosodic clustering process which is used to discretize phoneme-level F0 and duration features from a multispeaker speech dataset. These features are fed as an input sequence of prosodic labels to a prosody encoder module which augments an autoregressive attention-based text-to-speech model. We utilize various methods in order to improve prosodic control range and coverage, such as augmentation, F0 normalization, balanced clustering for duration and speaker-independent clustering. The final model enables fine-grained phoneme-level prosody control for all speakers contained in the training set, while maintaining the speaker identity. Instead of relying on reference utterances for inference, we introduce a prior prosody encoder which learns the style of each speaker and enables speech synthesis without the requirement of reference audio. We also fine-tune the multispeaker model to unseen speakers with limited amounts of data, as a realistic application scenario and show that the prosody control capabilities are maintained, verifying that the speaker-independent prosodic clustering is effective. Experimental results show that the model has high output speech quality and that the proposed method allows efficient prosody control within each speaker's range despite the variability that a multispeaker setting introduces.

我们介绍了一种无线文字语音转换（S2ST）系统，可以将来自一种语言的语音转换为另一种语言，并且可以在不需要任何文本数据的情况下构建。与文献中的现有工作不同，我们解决了模拟多扬声器目标语音的挑战，并用现实世界的S2ST数据训练系统。我们方法的关键是一种自我监督的单位语音标准化技术，该标准化技术将预先训练的语音编码器具有来自多个扬声器的配对声音，以及单个参考扬声器，以减少由于复印件引起的变化，同时保留词汇内容。只有10分钟的语音标准化的配对数据，我们在培训\ vp〜s2st数据集上的S2ST模型时获得平均3.2 BLEU增益，而不是在未标准化的语音目标上培训的基线。我们还将自动开采的S2ST数据纳入并显示额外的2.0 BLEU增益。据我们所知，我们是第一个建立无线的S2ST技术，可以用真实世界的数据培训，并为多种语言配对工作。

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative speech synthesis, where the system's output is synthesized by a neural vocoder after an inherently lossy feature-denoising step. In this paper, we propose a denoising vocoder (DeVo) approach, where a vocoder accepts noisy representations and learns to directly synthesize clean speech. We leverage rich representations from self-supervised learning (SSL) speech models to discover relevant features. We conduct a candidate search across 15 potential SSL front-ends and subsequently train our vocoder adversarially with the best SSL configuration. Additionally, we demonstrate a causal version capable of running on streaming audio with 10ms latency and minimal performance degradation. Finally, we conduct both objective evaluations and subjective listening studies to show our system improves objective metrics and outperforms an existing state-of-the-art SE model subjectively.

本文提出了一种表达语音合成架构，用于在单词级别建模和控制说话方式。它试图借助两个编码器来学习语音数据的单词级风格和韵律表示。通过查找声学特征的每个单词的样式令牌的组合，第二个模型样式，第二个输出单词级序列仅在语音信息上调节，以便从风格信息解开它。两个编码器输出与音素编码器输出对齐并连接，然后用非周度塔歇尔策略模型解码。额外的先前编码器用于自向预测样式标记，以便模型能够在没有参考话语的情况下运行。我们发现所产生的模型给出了对样式的单词级和全局控制，以及韵律转移能力。

神经文本到语音研究的最新进展是利用低级中间语音表示（例如MEL-光谱图）的两阶段管道主导的。但是，这种预定的特征从根本上受到限制，因为它们不允许通过学习隐藏表示形式来利用数据驱动方法的全部潜力。因此，已经提出了几种端到端方法。但是，这样的模型更难训练，并且需要大量具有转录的高质量录音。在这里，我们提出了WavThruvec-一种两阶段的架构，通过使用高维WAV2VEC 2.0嵌入作为中间语音表示，可以解决瓶颈。由于这些隐藏的激活提供了高级语言特征，因此它们对噪音更强大。这使我们能够利用质量较低的注释语音数据集来训练第一阶段模块。同时，由于WAV2VEC 2.0的嵌入已经进行了时间对齐，因此可以在大规模未转录的音频语料库上对第二阶段组件进行培训。这导致了对量表词的概括能力的提高，以及对看不见的说话者的更好概括。我们表明，所提出的模型不仅与最新神经模型的质量相匹配，而且还介绍了有用的属性，可以实现语音转换或零弹性合成的任务。

我们提出了一项对基于自我监督的语音表示（S3R）语音转换（VC）的大规模比较研究。在识别合成VC的背景下，S3RS由于其替代昂贵的监督表示的潜力，例如语音后验（PPG），因此很有吸引力，这些表示是由最先进的VC系统采用的。使用先前开发的开源VC软件S3PRL-VC，我们在三种VC设置下提供了一系列深入的目标和主观分析：内部/跨语义的任何一对一（A2O）和任何对象 - 使用语音转换挑战2020（VCC2020）数据集。我们在各个方面研究了基于S3R的VC，包括模型类型，多语言和监督。我们还研究了通过K-均值聚类的滴定过程的效果，并展示了其在A2A设置中的改进。最后，与最先进的VC系统的比较证明了基于S3R的VC的竞争力，并阐明了可能的改进方向。

Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these subjects and study Generalized Speech Enhancement, where the goal is not to reconstruct the exact reference clean signal, but to focus on improving certain aspects of speech. In particular, this paper concerns intelligibility, quality, and video synchronization. We cast the problem as audio-visual speech resynthesis, which is composed of two steps: pseudo audio-visual speech recognition (P-AVSR) and pseudo text-to-speech synthesis (P-TTS). P-AVSR and P-TTS are connected by discrete units derived from a self-supervised speech model. Moreover, we utilize self-supervised audio-visual speech model to initialize P-AVSR. The proposed model is coined ReVISE. ReVISE is the first high-quality model for in-the-wild video-to-speech synthesis and achieves superior performance on all LRS3 audio-visual enhancement tasks with a single model. To demonstrates its applicability in the real world, ReVISE is also evaluated on EasyCom, an audio-visual benchmark collected under challenging acoustic conditions with only 1.6 hours of training data. Similarly, ReVISE greatly suppresses noise and improves quality. Project page: https://wnhsu.github.io/ReVISE.