Related papers: Do self-supervised speech models develop human-lik…
To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…
Given the strong results of self-supervised models on various tasks, there have been surprisingly few studies exploring self-supervised representations for acoustic word embeddings (AWE), fixed-dimensional vectors representing…
Speech is the most natural way of expressing ourselves as humans. Identifying emotion from speech is a nontrivial task due to the ambiguous definition of emotion itself. Speaker Emotion Recognition (SER) is essential for understanding human…
Self-supervised speech models such as wav2vec2.0 and WavLM have been shown to significantly improve the performance of many downstream speech tasks, especially in low-resource settings, over the past few years. Despite this, evaluations on…
Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods…
Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…
Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…
Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to…
Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Association Test…
Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible: they require (1) extraordinarily large amounts…
While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…
Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them…
Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…
Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have…
Cued Speech (CS) is a communication system for deaf people or hearing impaired people, in which a speaker uses it to aid a lipreader in phonetic level by clarifying potentially ambiguous mouth movements with hand shape and positions.…
Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies…
Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer learning capabilities of such models on bioacoustic…
Neural network models using predictive coding are interesting from the viewpoint of computational modelling of human language acquisition, where the objective is to understand how linguistic units could be learned from speech without any…
It has been generally assumed in the automatic speech recognition (ASR) literature that it is better for models to have access to wider context windows. Yet, many of the potential reasons this might be true in the supervised setting do not…
This study asks how self-supervised speech models represent suprasegmental categories like Mandarin lexical tone, English lexical stress, and English phrasal accents. Through a series of probing tasks, we make layer-wise comparisons of…