语音合成

While recent large-scale neural codec language models have shown significant improvement in zero-shot TTS by training on thousands of hours of data, they suffer from drawbacks such as a lack of robustness, slow sampling speed similar to previous autoregressive TTS methods, and reliance on pre-trained neural codec representations. Our work proposes P-Flow, a fast and data-efficient zero-shot TTS model that uses speech prompts for speaker adaptation. P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis. Our speech-prompted text encoder uses speech prompts and text input to generate speaker-conditional text representation. The flow matching generative decoder uses the speaker-conditional output to synthesize high-quality personalized speech significantly faster than in real-time. Unlike the neural codec language models, we specifically train P-Flow on LibriTTS dataset using a continuous mel-representation. Through our training method using continuous speech prompts, P-Flow matches the speaker similarity performance of the large-scale zero-shot TTS models with two orders of magnitude less training data and has more than 20$\times$ faster sampling speed. Our results show that P-Flow has better pronunciation and is preferred in human likeness and speaker similarity to its recent state-of-the-art counterparts, thus defining P-Flow as an attractive and desirable alternative. We provide audio samples on our demo page: [https://research.nvidia.com/labs/adlr/projects/pflow](https://research.nvidia.com/labs/adlr/projects/pflow)

We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural question in the light of the excellent performance of such models in generating high-quality images. We consider specifically the Stable Diffusion, one of the leading open source text-to-image models. We show that (1) when the generative model is properly configured, training self-supervised methods on synthetic images can match or beat the real image counterpart; (2) by treating the multiple images generated from the same text prompt as positives for each other, we develop a multi-positive contrastive learning method, which we call StableRep. With solely synthetic images, the representations learned by StableRep surpass the performance of representations learned by SimCLR and CLIP using the same set of text prompts and corresponding real images, on large scale datasets. When we further add language supervision, \name~trained with 20M synthetic images (10M captions) achieves better accuracy than CLIP trained with 50M real images (50M captions).

Task-oriented dialogue (TOD) models have made significant progress in recent years. However, previous studies primarily focus on datasets written by annotators, which has resulted in a gap between academic research and real-world spoken con- versation scenarios. While several small-scale spoken TOD datasets are proposed to address robustness issues such as ASR errors, they ignore the unique challenges in spoken conversation. To tackle the limitations, we introduce SpokenWOZ, a large-scale speech-text dataset for spoken TOD, containing 8 domains, 203k turns, 5.7k dialogues and 249 hours of audios from human-to-human spoken conversations. SpokenWOZ further incorporates common spoken characteristics such as word-by-word processing and reasoning in spoken language. Based on these characteristics, we present cross-turn slot and reasoning slot detection as new challenges. We conduct experiments on various baselines, including text-modal models, newly proposed dual-modal models, and LLMs, e.g., ChatGPT. The results show that the current models still have substantial room for improvement in spoken conversation, where the most advanced dialogue state tracker only achieves 25.65% in joint goal accuracy and the SOTA end-to-end model only correctly completes the user request in 52.1% of dialogues. Our dataset, code, and leaderboard are available at https://spokenwoz.github.io/SpokenWOZ-github.io/.

Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of denoising iterations, making them computationally expensive and slow to run. As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale. This is costly and has privacy implications, especially when user data is sent to a third party. To overcome these challenges, we present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in **less than 2 seconds**. We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation. Further, we enhance the step distillation by exploring training strategies and introducing regularization from classifier-free guidance. Our extensive experiments on MS-COCO show that our model with $8$ denoising steps achieves better FID and CLIP scores than Stable Diffusion v$1.5$ with $50$ steps. Our work democratizes content creation by bringing powerful text-to-image diffusion models to the hands of users.

In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering. We show that these concepts complement each other and result in a strong representation learning model for speech. DinoSR first extracts contextualized embeddings from the input audio with a teacher network, then runs an online clustering system on the embeddings to yield a machine-discovered phone inventory, and finally uses the discretized tokens to guide a student network. We show that DinoSR surpasses previous state-of-the-art performance in several downstream tasks, and provide a detailed analysis of the model and the learned discrete units.

In-context vision and language models like Flamingo support arbitrarily interleaved sequences of images and text as input. This format not only enables few-shot learning via interleaving independent supervised (image, text) examples, but also, more complex prompts involving interaction between images, e.g., ``What do image A and image B have in common?'' To support this interface, pretraining occurs over web corpora that similarly contain interleaved images+text. To date, however, large-scale data of this form have not been publicly available. We release Multimodal C4, an augmentation of the popular text-only C4 corpus with images interleaved. We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives. Multimodal C4 spans everyday topics like cooking, travel, technology, etc. A manual inspection of a random sample of documents shows that a vast majority (88\%) of images are topically relevant, and that linear assignment frequently selects individual sentences specifically well-aligned with each image (80\%). After filtering NSFW images, ads, etc., the resulting corpus consists of 101.2M documents with 571M images interleaved in 43B English tokens.

We present \emph{DreamHuman}, a method to generate realistic animatable 3D human avatar models entirely from textual descriptions. Recent text-to-3D methods have made considerable strides in generation, but are still lacking in important aspects. Control and often spatial resolution remain limited, existing methods produce fixed rather than 3D human models that can be placed in different poses (i.e. re-posable or animatable), and anthropometric consistency for complex structures like people remains a challenge. \emph{DreamHuman} connects large text-to-image synthesis models, neural radiance fields, and statistical human body models in a novel optimization framework. This makes it possible to generate dynamic 3D human avatars with high-quality textures and learnt per-instance rigid and non rigid geometric deformations. We demonstrate that our method is capable to generate a wide variety of animatable, realistic 3D human models from text. These have diverse appearance, clothing, skin tones and body shapes, and outperform both generic text-to-3D approaches and previous text-based 3D avatar generators in visual fidelity.

This paper describes RETVec, an efficient, resilient, and multilingual text vectorizer designed for neural-based text processing. RETVec combines a novel character encoding with an optional small embedding model to embed words into a 256-dimensional vector space. The RETVec embedding model is pre-trained using pair-wise metric learning to be robust against typos and character-level adversarial attacks. In this paper, we evaluate and compare RETVec to state-of-the-art vectorizers and word embeddings on popular model architectures and datasets. These comparisons demonstrate that RETVec leads to competitive, multilingual models that are significantly more resilient to typos and adversarial text attacks. RETVec is available under the Apache 2 license at https://github.com/google-research/retvec.

There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with three LLMs show that this approach consistently improves their simple few-shot performance by roughly 10%, pushing the accuracy of LLMs towards SOTA or surpassing it. On the holdout test set of Spider, the SOTA, in terms of execution accuracy, was 79.9 and the new SOTA at the time of this writing using our approach is 85.3. Our approach with in-context learning beats many heavily fine-tuned models by at least 5%. Additionally, when evaluated on the BIRD benchmark, our approach achieved an execution accuracy of 55.9%, setting a new SOTA on its holdout test set.

Recent years have witnessed a surge of certified robust training pipelines against text adversarial perturbation constructed by synonym substitutions. Given a base model, existing pipelines provide prediction certificates either in the discrete word space or the continuous latent space. However, they are isolated from each other with a structural gap. We observe that existing training frameworks need unification to provide stronger certified robustness. Additionally, they mainly focus on building the certification process but neglect to improve the robustness of the base model. To mitigate the aforementioned limitations, we propose a unified framework named UniT that enables us to train flexibly in either fashion by working in the word embedding space. It can provide a stronger robustness guarantee obtained directly from the word embedding space without extra modules. In addition, we introduce the decoupled regularization (DR) loss to improve the robustness of the base model, which includes two separate robustness regularization terms for the feature extraction and classifier modules. Experimental results on widely used text classification datasets further demonstrate the effectiveness of the designed unified framework and the proposed DR loss for improving the certified robust accuracy.

Text-attributed graphs (TAGs) are prevalent in various real-world scenarios, where each node is associated with a text description. The cornerstone of representation learning on TAGs lies in the seamless integration of textual semantics within individual nodes and the topological connections across nodes. Recent advancements in pre-trained language models (PLMs) and graph neural networks (GNNs) have facilitated effective learning on TAGs, garnering increased research interest. However, the absence of meaningful benchmark datasets and standardized evaluation procedures for TAGs has impeded progress in this field. In this paper, we propose CS-TAG, a comprehensive and diverse collection of challenging benchmark datasets for TAGs. The CS-TAG datasets are notably large in scale and encompass a wide range of domains, spanning from citation networks to purchase graphs. In addition to building the datasets, we conduct extensive benchmark experiments over CS-TAG with various learning paradigms, including PLMs, GNNs, PLM-GNN co-training methods, and the proposed novel topological pre-training of language models. In a nutshell, we provide an overview of the CS-TAG datasets, standardized evaluation procedures, and present baseline experiments. The entire CS-TAG project is publicly accessible at \url{https://github.com/sktsherlock/TAG-Benchmark}.

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with our novel differentiable duration modeling for end-to-end training, resulting in improved speech naturalness. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. Moreover, when trained on the LibriTTS dataset, our model outperforms previous publicly available models for zero-shot speaker adaptation. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs. The audio demos and source code are available at https://styletts2.github.io/.

Diffusion models have gained increasing attention for their impressive generation abilities but currently struggle with rendering accurate and coherent text. To address this issue, we introduce TextDiffuser, focusing on generating images with visually appealing text that is coherent with backgrounds. TextDiffuser consists of two stages: first, a Transformer model generates the layout of keywords extracted from text prompts, and then diffusion models generate images conditioned on the text prompt and the generated layout. Additionally, we contribute the first large-scale text images dataset with OCR annotations, MARIO-10M, containing 10 million image-text pairs with text recognition, detection, and character-level segmentation annotations. We further collect the MARIO-Eval benchmark to serve as a comprehensive tool for evaluating text rendering quality. Through experiments and user studies, we demonstrate that TextDiffuser is flexible and controllable to create high-quality text images using text prompts alone or together with text template images, and conduct text inpainting to reconstruct incomplete images with text. We will make the code, model and dataset publicly available.

We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, completely side-stepping the time-consuming and costly process of manual annotation. We apply Cap3D to the recently introduced large-scale 3D dataset, Objaverse, resulting in 660k 3D-text pairs. Our evaluation, conducted using 41k human annotations from the same dataset, demonstrates that Cap3D surpasses human-authored descriptions in terms of quality, cost, and speed. Through effective prompt engineering, Cap3D rivals human performance in generating geometric descriptions on 17k collected annotations from the ABO dataset. Finally, we finetune Text-to-3D models on Cap3D and human captions, and show Cap3D outperforms; and benchmark the SOTA including Point·E, Shape·E, and DreamFusion.

Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of compositional capability, we design Cola, a text-to-image retrieval benchmark to Compose Objects Localized with Attributes. To solve Cola, a model must retrieve images with the correct configuration of attributes and objects and avoid choosing a distractor image with the same objects and attributes but in the wrong configuration. Cola contains about 1.2k composed queries of 168 objects and 197 attributes on around 30K images. Our human evaluation finds that Cola is 83.33% accurate, similar to contemporary compositionality benchmarks. Using Cola as a testbed, we explore empirical modeling designs to adapt pre-trained vision-language models to reason compositionally. We explore 6 adaptation strategies on 2 seminal vision-language models, using compositionality-centric test benchmarks - Cola and CREPE. We find the optimal adaptation strategy is to train a multi-modal attention layer that jointly attends over the frozen pre-trained image and language features. Surprisingly, training multimodal layers on CLIP performs better than tuning a larger FLAVA model with already pre-trained multimodal layers. Furthermore, our adaptation strategy improves CLIP and FLAVA to comparable levels, suggesting that training multimodal layers using contrastive attribute-object data is key, as opposed to using them pre-trained. Lastly, we show that Cola is harder than a closely related contemporary benchmark, CREPE, since simpler fine-tuning strategies without multimodal layers suffice on CREPE, but not on Cola. However, we still see a significant gap between our best adaptation and human accuracy, suggesting considerable room for further research. Project page: https://cs-people.bu.edu/array/research/cola/

A good supervised embedding for a specific machine learning task is only sensitive to changes in the label of interest and is invariant to other confounding factors. We leverage the concept of repeatability from measurement theory to describe this property and propose to use the intra-class correlation coefficient (ICC) to evaluate the repeatability of embeddings. We then propose a novel regularizer, the ICC regularizer, as a complementary component for contrastive losses to guide deep neural networks to produce embeddings with higher repeatability. We use simulated data to explain why the ICC regularizer works better on minimizing the intra-class variance than the contrastive loss alone. We implement the ICC regularizer and apply it to three speech tasks: speaker verification, voice style conversion, and a clinical application for detecting dysphonic voice. The experimental results demonstrate that adding an ICC regularizer can improve the repeatability of learned embeddings compared to only using the contrastive loss; further, these embeddings lead to improved performance in these downstream tasks.

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For instance, recent work has shown that CLIP image representations are often biased toward specific visual properties (such as objects or actions) in an unpredictable manner. In this paper, we propose to separate representations of the different visual modalities in CLIP’s joint vision-language space by leveraging the association between parts of speech and specific visual modes of variation (e.g. nouns relate to objects, adjectives describe appearance). This is achieved by formulating an appropriate component analysis model that learns subspaces capturing variability corresponding to a specific part of speech, while jointly minimising variability to the rest. Such a subspace yields disentangled representations of the different visual properties of an image or text in closed form while respecting the underlying geometry of the manifold on which the representations lie. What’s more, we show the proposed model additionally facilitates learning subspaces corresponding to specific visual appearances (e.g. artists’ painting styles), which enables the selective removal of entire visual themes from CLIP-based text-to-image synthesis. We validate the model both qualitatively, by visualising the subspace projections with a text-to-image model and by preventing the imitation of artists’ styles, and quantitatively, through class invariance metrics and improvements to baseline zero-shot classification.

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://github.com/CVI-SZU/UniTSFace.

Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9\% vs 1.9\% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster. Audio samples can be found in \url{https://voicebox.metademolab.com}.

Existing full text datasets of U.S. public domain newspapers do not recognize the often complex layouts of newspaper scans, and as a result the digitized content scrambles texts from articles, headlines, captions, advertisements, and other layout regions. OCR quality can also be low. This study develops a novel, deep learning pipeline for extracting full article texts from newspaper images and applies it to the nearly 20 million scans in Library of Congress's public domain Chronicling America collection. The pipeline includes layout detection, legibility classification, custom OCR, and association of article texts spanning multiple bounding boxes. To achieve high scalability, it is built with efficient architectures designed for mobile phones. The resulting American Stories dataset provides high quality data that could be used for pre-training a large language model to achieve better understanding of historical English and historical world knowledge. The dataset could also be added to the external database of a retrieval-augmented language model to make historical information - ranging from interpretations of political events to minutiae about the lives of people's ancestors - more widely accessible. Furthermore, structured article texts facilitate using transformer-based methods for popular social science applications like topic classification, detection of reproduced content, and news story clustering. Finally, American Stories provides a massive silver quality dataset for innovating multimodal layout analysis models and other multimodal applications.