A Meghanani, T Hain - arXiv preprint arXiv:2403.08738, 2024 - arxiv.org
Acoustic word embeddings (AWEs) are vector representations of spoken words. An effective method for obtaining AWEs is the Correspondence Auto-Encoder (CAE). In the past, the …
Given the strong results of self-supervised models on various tasks, there have been surprisingly few studies exploring self-supervised representations for acoustic word …
J Lin, X Yue, J Ao, H Li - arXiv preprint arXiv:2307.09871, 2023 - arxiv.org
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 …
A Saliba, Y Li, R Sanabria, C Lai - arXiv preprint arXiv:2402.02617, 2024 - arxiv.org
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 …
Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one …
S Ram, H Aldarmaki - arXiv preprint arXiv:2301.01020, 2023 - arxiv.org
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 …
Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic …
Recent studies have introduced methods for learning acoustic word embeddings (AWEs)--- fixed-size vector representations of words which encode their acoustic features. Despite the …
Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate …