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.

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。

本文介绍了一种在自回归关注文本到语音系统中控制音素级别的韵律的方法。除了通常完成的常见框架中，我们将从培训集中的语音数据中直接提取音素级F0和持续时间特征，而不是学习潜在韵律特征。每个韵律特征是使用无监督聚类离散化，以便为每个话语产生一系列韵律标签。该序列与音素序列并行使用，以便通过利用韵律编码器和相应的注意模块来调节解码器。实验结果表明，该方法保留了高质量的生成语音，同时允许对F0和持续时间进行音素级控制。通过用音符替换F0集群质心，该模型还可以在扬声器范围内提供对音符和八度音的控制。

本文介绍了对F0的音素级韵律控制的方法和多销箱文本到语音设置的持续时间，基于韵律聚类。使用自回归关注的模型，并将多个箱子架构模块并联，与韵律编码器并联。提出了对基本单扬声器方法的几种改进，从而增加了韵律控制范围和覆盖范围。更具体地说，我们采用数据增强，F0​​标准化，持续时间的平衡集群，以及扬声器无关的韵律聚类。这些修改使培训集中包含的所有发言者能够进行细粒度的音素级韵律控制，同时保持扬声器标识。该模型也可以微调到具有限制数据量的看不见的扬声器，并显示其维持其韵律控制能力，验证说话者无关的韵律聚类是有效的。实验结果验证了该模型维持了高输出语音质量，并且该方法允许在每个扬声器范围内有效的韵律控制，尽管多种式箱子设置介绍的变化。

在本文中，介绍了文本到读取/唱歌系统，可以适应任何扬声器的声音。它利用基于TacoTron的多级箱子声学模型在只读语音数据训练，并且在音素级别提供韵律控制。还研究了基于传统DSP算法的数据集增强和额外的韵律操纵。神经TTS模型对看不见的扬声器的有限录音进行了微调，允许与目标的扬声器语音进行敲击/歌唱合成。描述了系统的详细管道，其包括从Capella歌曲的目标音调和持续时间值提取，并将其转换为在合成之前的目标扬声器的有效音符范围内。还研究了通过WSOLA输出的输出的韵律操纵的另外的阶段，以便更好地匹配目标持续时间值。合成的话语可以与乐器伴奏轨道混合以产生完整的歌曲。通过主观聆听测试评估所提出的系统，以及与可用的备用系统相比，该系统还旨在从只读训练数据产生合成歌唱语音。结果表明，该拟议的方法可以产生高质量的敲击/歌声，具有增加的自然。

Task-oriented dialogue (TOD) systems have been applied in a range of domains to support human users to achieve specific goals. Systems are typically constructed for a single domain or language and do not generalise well beyond this. Their extension to other languages in particular is restricted by the lack of available training data for many of the world's languages. To support work on Natural Language Understanding (NLU) in TOD across multiple languages and domains simultaneously, we constructed MULTI3NLU++, a multilingual, multi-intent, multi-domain dataset. MULTI3NLU++ extends the English-only NLU++ dataset to include manual translations into a range of high, medium and low resource languages (Spanish, Marathi, Turkish and Amharic), in two domains (banking and hotels). MULTI3NLU++ inherits the multi-intent property of NLU++, where an utterance may be labelled with multiple intents, providing a more realistic representation of a user's goals and aligning with the more complex tasks that commercial systems aim to model. We use MULTI3NLU++ to benchmark state-of-the-art multilingual language models as well as Machine Translation and Question Answering systems for the NLU task of intent detection for TOD systems in the multilingual setting. The results demonstrate the challenging nature of the dataset, particularly in the low-resource language setting.

Automatic machine translation (MT) metrics are widely used to distinguish the translation qualities of machine translation systems across relatively large test sets (system-level evaluation). However, it is unclear if automatic metrics are reliable at distinguishing good translations from bad translations at the sentence level (segment-level evaluation). In this paper, we investigate how useful MT metrics are at detecting the success of a machine translation component when placed in a larger platform with a downstream task. We evaluate the segment-level performance of the most widely used MT metrics (chrF, COMET, BERTScore, etc.) on three downstream cross-lingual tasks (dialogue state tracking, question answering, and semantic parsing). For each task, we only have access to a monolingual task-specific model. We calculate the correlation between the metric's ability to predict a good/bad translation with the success/failure on the final task for the Translate-Test setup. Our experiments demonstrate that all metrics exhibit negligible correlation with the extrinsic evaluation of the downstream outcomes. We also find that the scores provided by neural metrics are not interpretable mostly because of undefined ranges. Our analysis suggests that future MT metrics be designed to produce error labels rather than scores to facilitate extrinsic evaluation.

Many state-of-the-art natural language understanding (NLU) models are based on pretrained neural language models. These models often make inferences using information from multiple sources. An important class of such inferences are those that require both background knowledge, presumably contained in a model's pretrained parameters, and instance-specific information that is supplied at inference time. However, the integration and reasoning abilities of NLU models in the presence of multiple knowledge sources have been largely understudied. In this work, we propose a test suite of coreference resolution tasks that require reasoning over multiple facts. Our dataset is organized into subtasks that differ in terms of which knowledge sources contain relevant facts. We evaluate state-of-the-art coreference resolution models on our dataset. Our results indicate that several models struggle to reason on-the-fly over knowledge observed both at pretrain time and at inference time. However, with task-specific training, a subset of models demonstrates the ability to integrate certain knowledge types from multiple sources.

Monocular Depth Estimation (MDE) is a fundamental problem in computer vision with numerous applications. Recently, LIDAR-supervised methods have achieved remarkable per-pixel depth accuracy in outdoor scenes. However, significant errors are typically found in the proximity of depth discontinuities, i.e., depth edges, which often hinder the performance of depth-dependent applications that are sensitive to such inaccuracies, e.g., novel view synthesis and augmented reality. Since direct supervision for the location of depth edges is typically unavailable in sparse LIDAR-based scenes, encouraging the MDE model to produce correct depth edges is not straightforward. In this work we propose to learn to detect the location of depth edges from densely-supervised synthetic data, and use it to generate supervision for the depth edges in the MDE training. %Despite the 'domain gap' between synthetic and real data, we show that depth edges that are estimated directly are significantly more accurate than the ones that emerge indirectly from the MDE training. To quantitatively evaluate our approach, and due to the lack of depth edges ground truth in LIDAR-based scenes, we manually annotated subsets of the KITTI and the DDAD datasets with depth edges ground truth. We demonstrate significant gains in the accuracy of the depth edges with comparable per-pixel depth accuracy on several challenging datasets.

Detecting personal health mentions on social media is essential to complement existing health surveillance systems. However, annotating data for detecting health mentions at a large scale is a challenging task. This research employs a multitask learning framework to leverage available annotated data from a related task to improve the performance on the main task to detect personal health experiences mentioned in social media texts. Specifically, we focus on incorporating emotional information into our target task by using emotion detection as an auxiliary task. Our approach significantly improves a wide range of personal health mention detection tasks compared to a strong state-of-the-art baseline.