Related papers: Supervised Contrastive Learning with Nearest Neigh…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

In dialogue systems, utterances with similar semantics may have distinctive emotions under different contexts. Therefore, modeling long-range contextual emotional relationships with speaker dependency plays a crucial part in dialogue…

Emotion recognition in conversations (ERC) is a rapidly evolving task within the natural language processing community, which aims to detect the emotions expressed by speakers during a conversation. Recently, a growing number of ERC methods…

Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. Recently, to alleviate expensive data collection, co-occurring pairs from the Internet are automatically harvested for training. However, it…

Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-modality learning tasks…

Contrastive learning, especially self-supervised contrastive learning (SSCL), has achieved great success in extracting powerful features from unlabeled data. In this work, we contribute to the theoretical understanding of SSCL and uncover…

Speech Emotion Recognition (SER) systems often degrade in performance when exposed to the unpredictable acoustic interference found in real-world environments. Additionally, the opacity of deep learning models hinders their adoption in…

Self-supervised learning (SSL) is the latest breakthrough in speech processing, especially for label-scarce downstream tasks by leveraging massive unlabeled audio data. The noise robustness of the SSL is one of the important challenges to…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider…

Unsupervised speech emotion recognition (SER) focuses on addressing the problem of data sparsity and annotation bias of emotional speech. Reinforcement learning (RL) is a promising method which enhances the performance through rule-based or…

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…

Recent studies have explored the use of pre-trained embeddings for speech emotion recognition (SER), achieving comparable performance to conventional methods that rely on low-level knowledge-inspired acoustic features. These embeddings are…

Alongside acoustic information, linguistic features based on speech transcripts have been proven useful in Speech Emotion Recognition (SER). However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional…

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR…

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an…

There is an imminent need for guidelines and standard test sets to allow direct and fair comparisons of speech emotion recognition (SER). While resources, such as the Interactive Emotional Dyadic Motion Capture (IEMOCAP) database, have…