In this paper, we present a methodology for linguistic feature extraction, focusing particularly on automatically syllabifying words in multiple languages, with a design to be compatible with a forced-alignment tool, the Montreal Forced Aligner (MFA). In both the textual and phonetic domains, our method focuses on the extraction of phonetic transcriptions from text, stress marks, and a unified automatic syllabification (in text and phonetic domains). The system was built with open-source components and resources. Through an ablation study, we demonstrate the efficacy of our approach in automatically syllabifying words from several languages (English, French and Spanish). Additionally, we apply the technique to the transcriptions of the CMU ARCTIC dataset, generating valuable annotations available online\footnote{\url{https://github.com/noetits/MUST_P-SRL}} that are ideal for speech representation learning, speech unit discovery, and disentanglement of speech factors in several speech-related fields.
Layout-to-image synthesis is an emerging technique in conditional image generation. It aims to generate complex scenes, where users require fine control over the layout of the objects in a scene. However, it remains challenging to control the object coherence, including semantic coherence (e.g., the cat looks at the flowers or not) and physical coherence (e.g., the hand and the racket should not be misaligned). In this paper, we propose a novel diffusion model with effective global semantic fusion (GSF) and self-similarity feature enhancement modules to guide the object coherence for this task. For semantic coherence, we argue that the image caption contains rich information for defining the semantic relationship within the objects in the images. Instead of simply employing cross-attention between captions and generated images, which addresses the highly relevant layout restriction and semantic coherence separately and thus leads to unsatisfying results shown in our experiments, we develop GSF to fuse the supervision from the layout restriction and semantic coherence requirement and exploit it to guide the image synthesis process. Moreover, to improve the physical coherence, we develop a Self-similarity Coherence Attention (SCA) module to explicitly integrate local contextual physical coherence into each pixel's generation process. Specifically, we adopt a self-similarity map to encode the coherence restrictions and employ it to extract coherent features from text embedding. Through visualization of our self-similarity map, we explore the essence of SCA, revealing that its effectiveness is not only in capturing reliable physical coherence patterns but also in enhancing complex texture generation. Extensive experiments demonstrate the superiority of our proposed method in both image generation quality and controllability.
Large-scale noisy web image-text datasets have been proven to be efficient for learning robust vision-language models. However, when transferring them to the task of video retrieval, models still need to be fine-tuned on hand-curated paired text-video data to adapt to the diverse styles of video descriptions. To address this problem without the need for hand-annotated pairs, we propose a new setting, text-video retrieval with uncurated & unpaired data, that during training utilizes only text queries together with uncurated web videos without any paired text-video data. To this end, we propose an approach, In-Style, that learns the style of the text queries and transfers it to uncurated web videos. Moreover, to improve generalization, we show that one model can be trained with multiple text styles. To this end, we introduce a multi-style contrastive training procedure that improves the generalizability over several datasets simultaneously. We evaluate our model on retrieval performance over multiple datasets to demonstrate the advantages of our style transfer framework on the new task of uncurated & unpaired text-video retrieval and improve state-of-the-art performance on zero-shot text-video retrieval.
Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question answering (OK-VQA). As images are invisible to LLMs, researchers convert images to text to engage LLMs into the visual question reasoning procedure. This leads to discrepancies between images and their textual representations presented to LLMs, which consequently impedes final reasoning performance. To fill the information gap and better leverage the reasoning capability, we design a framework that enables LLMs to proactively ask relevant questions to unveil more details in the image, along with filters for refining the generated information. We validate our idea on OK-VQA and A-OKVQA. Our method continuously boosts the performance of baselines methods by an average gain of 2.15% on OK-VQA, and achieves consistent improvements across different LLMs.
Text-to-image generation is a significant domain in modern computer vision and has achieved substantial improvements through the evolution of generative architectures. Among these, there are diffusion-based models that have demonstrated essential quality enhancements. These models are generally split into two categories: pixel-level and latent-level approaches. We present Kandinsky1, a novel exploration of latent diffusion architecture, combining the principles of the image prior models with latent diffusion techniques. The image prior model is trained separately to map text embeddings to image embeddings of CLIP. Another distinct feature of the proposed model is the modified MoVQ implementation, which serves as the image autoencoder component. Overall, the designed model contains 3.3B parameters. We also deployed a user-friendly demo system that supports diverse generative modes such as text-to-image generation, image fusion, text and image fusion, image variations generation, and text-guided inpainting/outpainting. Additionally, we released the source code and checkpoints for the Kandinsky models. Experimental evaluations demonstrate a FID score of 8.03 on the COCO-30K dataset, marking our model as the top open-source performer in terms of measurable image generation quality.
Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lacks the essential metadata required for researchers to find and search them effectively. The lack of metadata poses a significant challenge in the utilization of these datasets. Machine learning-based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific datasets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata. However, manual labeling is time-consuming; thus, there is an need to develop automated text labeling techniques in order to accelerate the process of scientific innovation. This need is particularly urgent in fields such as environmental genomics and microbiome science, which have historically received less attention in terms of metadata curation and creation of gold-standard text mining datasets. In this paper, we present two novel automated text labeling approaches for the validation of ML-generated metadata for unlabeled texts, with specific applications in environmental genomics. Our techniques show the potential of two new ways to leverage existing information about the unlabeled texts and the scientific domain. The first technique exploits relationships between different types of data sources related to the same research study, such as publications and proposals. The second technique takes advantage of domain-specific controlled vocabularies or ontologies. In this paper, we detail applying these approaches for ML-generated metadata validation. Our results show that the proposed label assignment approaches can generate both generic and highly-specific text labels for the unlabeled texts, with up to 44% of the labels matching with those suggested by a ML keyword extraction algorithm.
Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. However, there has been significantly less work on the zero-shot abilities of ASR foundation models, with these systems typically fine-tuned to specific tasks or constrained to applications that match their training criterion and data annotation. In this work we investigate the ability of Whisper and MMS, ASR foundation models trained primarily for speech recognition, to perform zero-shot audio classification. We use simple template-based text prompts at the decoder and use the resulting decoding probabilities to generate zero-shot predictions. Without training the model on extra data or adding any new parameters, we demonstrate that Whisper shows promising zero-shot classification performance on a range of 8 audio-classification datasets, outperforming existing state-of-the-art zero-shot baseline's accuracy by an average of 9%. One important step to unlock the emergent ability is debiasing, where a simple unsupervised reweighting method of the class probabilities yields consistent significant performance gains. We further show that performance increases with model size, implying that as ASR foundation models scale up, they may exhibit improved zero-shot performance.
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives. This downstream performance can further be enhanced by full-scale fine-tuning which is often compute intensive, requires large labelled data, and can reduce out-of-distribution (OOD) robustness. Furthermore, sole reliance on inter-modal alignment might overlook the rich information embedded within each individual modality. In this work, we introduce a sample-efficient domain adaptation strategy for CLIP, termed Domain Aligned CLIP (DAC), which improves both intra-modal (image-image) and inter-modal alignment on target distributions without fine-tuning the main model. For intra-modal alignment, we introduce a lightweight adapter that is specifically trained with an intra-modal contrastive objective. To improve inter-modal alignment, we introduce a simple framework to modulate the precomputed class text embeddings. The proposed few-shot fine-tuning framework is computationally efficient, robust to distribution shifts, and does not alter CLIP's parameters. We study the effectiveness of DAC by benchmarking on 11 widely used image classification tasks with consistent improvements in 16-shot classification upon strong baselines by about 2.3% and demonstrate competitive performance on 4 OOD robustness benchmarks.
Recent improvements in text generation have leveraged human feedback to improve the quality of the generated output. However, human feedback is not always available, especially during inference. In this work, we propose an inference time optimization method FITO to use fine-grained actionable feedback in the form of error type, error location and severity level that are predicted by a learned error pinpoint model for iterative refinement. FITO starts with an initial output, then iteratively incorporates the feedback via a refinement model that generates an improved output conditioned on the feedback. Given the uncertainty of consistent refined samples at iterative steps, we formulate iterative refinement into a local search problem and develop a simulated annealing based algorithm that balances exploration of the search space and optimization for output quality. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA) and topical summarization. We observe 0.8 and 0.7 MetricX gain on Chinese-English and English-German translation, 4.5 and 1.8 ROUGE-L gain at long form QA and topic summarization respectively, with a single iteration of refinement. With our simulated annealing algorithm, we see further quality improvements, including up to 1.7 MetricX improvements over the baseline approach.
Despite known differences between reading and listening in the brain, recent work has shown that text-based language models predict both text-evoked and speech-evoked brain activity to an impressive degree. This poses the question of what types of information language models truly predict in the brain. We investigate this question via a direct approach, in which we eliminate information related to specific low-level stimulus features (textual, speech, and visual) in the language model representations, and observe how this intervention affects the alignment with fMRI brain recordings acquired while participants read versus listened to the same naturalistic stories. We further contrast our findings with speech-based language models, which would be expected to predict speech-evoked brain activity better, provided they model language processing in the brain well. Using our direct approach, we find that both text-based and speech-based language models align well with early sensory regions due to shared low-level features. Text-based models continue to align well with later language regions even after removing these features, while, surprisingly, speech-based models lose most of their alignment. These findings suggest that speech-based models can be further improved to better reflect brain-like language processing.