Related papers: Self-supervised language learning from raw audio: …

Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised…

Speech separation is the task of separating target speech from background interference. Traditionally, speech separation is studied as a signal processing problem. A more recent approach formulates speech separation as a supervised learning…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Self-supervision has recently shown great promise for learning visual and auditory speech representations from unlabelled data. In this work, we propose BRAVEn, an extension to the recent RAVEn method, which learns speech representations…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

Representing speech and audio signals in discrete units has become a compelling alternative to traditional high-dimensional feature vectors. Numerous studies have highlighted the efficacy of discrete units in various applications such as…

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…

Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score…

Sustainable artificial intelligence focuses on data, hardware, and algorithms to make machine learning models more environmentally responsible. In particular, machine learning models for speech representations are computationally expensive,…

The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of…

This paper presents a brief survey on Automatic Speech Recognition and discusses the major themes and advances made in the past 60 years of research, so as to provide a technological perspective and an appreciation of the fundamental…

Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very…

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…

Large scale databases with high-quality manual annotations are scarce in audio domain. We thus explore a self-supervised graph approach to learning audio representations from highly limited labelled data. Considering each audio sample as a…

This work describes our group's submission to the PROCESS Challenge 2024, with the goal of assessing cognitive decline through spontaneous speech, using three guided clinical tasks. This joint effort followed a holistic approach,…

Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have further expanded this capability to perceive multimodal audio…

Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide…

The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have…

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…