相关论文: Large Language Models Meet Contrastive Learning: Z…

In this paper, we introduce MultiviewVLM, a vision-language model designed for unsupervised contrastive multiview representation learning of facial emotions from 3D/4D data. Our architecture integrates pseudo-labels derived from generated…

Zero-shot learning models are capable of classifying new classes by transferring knowledge from the seen classes using auxiliary information. While most of the existing zero-shot learning methods focused on single-label classification…

Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used…

Human beings have rich ways of emotional expressions, including facial action, voice, and natural languages. Due to the diversity and complexity of different individuals, the emotions expressed by various modalities may be semantically…

Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the…

We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the…

Emotion recognition in conversations is essential for ensuring advanced human-machine interactions. However, creating robust and accurate emotion recognition systems in real life is challenging, mainly due to the scarcity of emotion…

Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works…

Hate speech detection has become an important research topic within the past decade. More private corporations are needing to regulate user generated content on different platforms across the globe. In this paper, we introduce a study of…

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic…

Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…

Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…

Emotion recognition is a topic of significant interest in assistive robotics due to the need to equip robots with the ability to comprehend human behavior, facilitating their effective interaction in our society. Consequently, efficient and…

Recently there has been a significant surge in multimodal learning in terms of both image-to-text and text-to-image generation. However, the success is typically limited to English, leaving other languages largely behind. Building a…

Speech Emotion Recognition (SER) is a challenging task due to limited data and blurred boundaries of certain emotions. In this paper, we present a comprehensive approach to improve the SER performance throughout the model lifecycle,…

The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approach is useful for code-switching, as it facilitates the…

Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems. These methods have achieved great success via learning intermediate…

Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image…

Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading…

Traditionally, in paralinguistic analysis for emotion detection from speech, emotions have been identified with discrete or dimensional (continuous-valued) labels. Accordingly, models that have been proposed for emotion detection use one or…