Related papers: Rethinking Continual Learning for Speech and Audio…

A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural…

Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies…

Spoken Language Assessment (SLA) estimates a learner's oral proficiency from spontaneous speech. The growing population of L2 English speakers has intensified the demand for reliable SLA, a critical component of Computer Assisted Language…

Enhancing explainability in speech self-supervised learning (SSL) is important for developing reliable SSL-based speech processing systems. This study probes how speech SSL models encode speaker-specific information via a large-scale…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers…

We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before. CL is a very active recent research topic concerned…

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar…

This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully}…

The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approach to self-supervised representation learning from raw audio…

Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Continual learning (CL) is crucial for evaluating adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they…

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

With the rise of Speech Large Language Models (SpeechLLMs), two dominant approaches have emerged for speech processing: discrete tokens and continuous features. Each approach has demonstrated strong capabilities in audio-related processing…

Diffusion models have emerged as a promising alternative to autoregressive models in modeling discrete categorical data. However, diffusion models that directly work on discrete data space fail to fully exploit the power of iterative…

In second language learning, scenario-based conversation practice is important for language learners to achieve fluency in speaking, but students often lack sufficient opportunities to practice their conversational skills with qualified…