Related papers: Augment, Drop & Swap: Improving Diversity in LLM C…
Modeling temporal characteristics plays a significant role in the representation learning of audio waveform. We propose Contrastive Long-form Language-Audio Pretraining (\textbf{CoLLAP}) to significantly extend the perception window for…
In this work, we investigate an approach that relies on contrastive learning and music metadata as a weak source of supervision to train music representation models. Recent studies show that contrastive learning can be used with editorial…
Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for…
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise…
The effectiveness of contrastive learning in sequential recommendation hinges on the construction of contrastive views, which ideally should be both semantically consistent and diverse. However, most existing CL-based methods rely on…
While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair data for training and performance degradation when…
Audio embeddings are crucial tools in understanding large catalogs of music. Typically embeddings are evaluated on the basis of the performance they provide in a wide range of downstream tasks, however few studies have investigated the…
We introduce CLaMP: Contrastive Language-Music Pre-training, which learns cross-modal representations between natural language and symbolic music using a music encoder and a text encoder trained jointly with a contrastive loss. To pre-train…
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…
Data augmentation techniques are widely used in text classification tasks to improve the performance of classifiers, especially in low-resource scenarios. Most previous methods conduct text augmentation without considering the different…
This paper introduces the ColorSwap dataset, designed to assess and improve the proficiency of multimodal models in matching objects with their colors. The dataset is comprised of 2,000 unique image-caption pairs, grouped into 1,000…
Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and text. However, their performance in handling conflicting…
Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are…
Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data. Recent work on contrastive losses for learning joint embeddings over multimodal data has been successful at tasks such as retrieval and…
Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…
Text embeddings, i.e. vector representations of entire texts, play an important role in many NLP applications, such as retrieval-augmented generation, clustering, or visualizing collections of texts for data exploration. Currently,…
Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…
Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the success, generating data augmentations as hard positive examples…
This paper explores the use of text data augmentation techniques to enhance conflict and duplicate detection in software engineering tasks through sentence pair classification. The study adapts generic augmentation techniques such as…
Self-supervised contrastive learning is among the recent representation learning methods that have shown performance gains in several downstream tasks including semantic segmentation. This paper evaluates strong data augmentation, one of…