Related papers: HARNESS: Lightweight Distilled Arabic Speech Found…

Developing Automatic Speech Recognition (ASR) systems for Tunisian Arabic Dialect is challenging due to the dialect's linguistic complexity and the scarcity of annotated speech datasets. To address these challenges, we propose the LinTO…

Language-queried Audio Separation (LASS) employs linguistic queries to isolate target sounds based on semantic descriptions. However, existing methods face challenges in aligning complex auditory features with linguistic context while…

Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this work, we present DistilQwen2.5, a family of distilled,…

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains…

This paper presents a novel knowledge distillation method for dialogue sequence labeling. Dialogue sequence labeling is a supervised learning task that estimates labels for each utterance in the target dialogue document, and is useful for…

Speech-based AI educational applications have gained significant interest in recent years, particularly for children. However, children speech research remains limited due to the lack of publicly available datasets, especially for…

In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering. We show that these concepts…

Over the last decade, deep-learning methods have been gradually incorporated into conventional automatic speech recognition (ASR) frameworks to create acoustic, pronunciation, and language models. Although it led to significant improvements…

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase,…

Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we focus on knowledge distillation for the RNN-T model,…

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive Transformers, limiting their scope of applications under…

This paper presents an Arabic Alphabet Sign Language recognition approach, using deep learning methods in conjunction with transfer learning and transformer-based models. We study the performance of the different variants on two publicly…

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing…

Speech Emotion Recognition (SER) has significant potential for mobile applications, yet deployment remains constrained by the computational demands of state-of-the-art transformer architectures. This paper presents a mobile-efficient SER…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

The rise of social media and online communication platforms has led to the spread of Arabic textual posts and memes as a key form of digital expression. While these contents can be humorous and informative, they are also increasingly being…

In this paper, we introduce SaudiBERT, a monodialect Arabic language model pretrained exclusively on Saudi dialectal text. To demonstrate the model's effectiveness, we compared SaudiBERT with six different multidialect Arabic language…

In recent years, self-supervised learning (SSL) has achieved tremendous success in various speech tasks due to its power to extract representations from massive unlabeled data. However, compared with tasks such as speech recognition (ASR),…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ…