Related papers: Leveraging Semantic Information for Efficient Self…
Recently, there has been a vast interest in self-supervised learning (SSL) where the model is pre-trained on large scale unlabeled data and then fine-tuned on a small labeled dataset. The common wisdom is that SSL helps resource-limited…
Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…
With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate…
Recently, pre-trained models for music information retrieval based on self-supervised learning (SSL) are becoming popular, showing success in various downstream tasks. However, there is limited research on the specific meanings of the…
Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand…
Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains.…
Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data to learn useful features for downstream classification…
Self-supervised learning (SSL) is a powerful technique for learning representations from unlabeled data. Transformer based models such as HuBERT, which consist a feature extractor and transformer layers, are leading the field in the speech…
State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two…
Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…
Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their…
Speech emotion recognition predicts a speaker's emotional state from speech signals using discrete labels or continuous dimensions such as arousal, valence, and dominance (VAD). We propose EmoSphere-SER, a joint model that integrates…
While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised…
Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…
Medical instrument segmentation in 3D ultrasound is essential for image-guided intervention. However, to train a successful deep neural network for instrument segmentation, a large number of labeled images are required, which is expensive…
Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction. However, building robust multilingual SER systems remains challenging due to the scarcity of…
This research presents a hybrid emotion recognition system integrating advanced Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs) to analyze audio and textual data for enhancing customer interactions in…
Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models with fewer than 500K parameters. We identify three obstacles at this scale -- projection…
This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a…
Speech emotion recognition (SER) systems find applications in various fields such as healthcare, education, and security and defense. A major drawback of these systems is their lack of generalization across different conditions. This…