Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Abstract Automatic Speech Recognition (ASR) systems can be trained to achieve
remarkable performance given large amounts of manually transcribed speech, but large …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
improving performance and data efficiency on various speech tasks. However, these …

Given the strong results of self-supervised models on various tasks, there have been
surprisingly few studies exploring self-supervised representations for acoustic word …

The efficacy of self-supervised speech models has been validated, yet the optimal utilization
of their representations remains challenging across diverse tasks. In this study, we delve into …

In NLP, text language models based on words or subwords are known to outperform their
character-based counterparts. Yet, in the speech community, the standard input of spoken …

Voice assistive technologies have given rise to far-reaching privacy and security concerns.
In this paper we investigate whether modular automatic speech recognition (ASR) can …

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a
fixed-dimensional representation. High-quality AWEs should be invariant to variations, such …

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 …

We propose direct multimodal few-shot models that learn a shared embedding space of
spoken words and images from only a few paired examples. Imagine an agent is shown an …