A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings
L Van Staden, H Kamper - 2021 IEEE Spoken Language …, 2021 - ieeexplore.ieee.org
Many speech processing tasks involve measuring the acoustic similarity between speech
segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping …
segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping …
Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations
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 …
method for obtaining AWEs is the Correspondence Auto-Encoder (CAE). In the past, the …
Analyzing acoustic word embeddings from pre-trained self-supervised speech models
Given the strong results of self-supervised models on various tasks, there have been
surprisingly few studies exploring self-supervised representations for acoustic word …
surprisingly few studies exploring self-supervised representations for acoustic word …
Self-supervised acoustic word embedding learning via correspondence transformer encoder
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 …
fixed-dimensional representation. High-quality AWEs should be invariant to variations, such …
Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition
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 …
of their representations remains challenging across diverse tasks. In this study, we delve into …
Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
C Jacobs, Y Matusevych… - 2021 IEEE Spoken …, 2021 - ieeexplore.ieee.org
Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length
speech segments. For zero-resource languages where labelled data is not available, one …
speech segments. For zero-resource languages where labelled data is not available, one …
Supervised acoustic embeddings and their transferability across languages
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 …
discarding irrelevant factors such as speaker variations and noise, which is challenging in …
Integrating form and meaning: A multi-task learning model for acoustic word embeddings
Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word
segments onto fixed-dimensionality vector representations such that different acoustic …
segments onto fixed-dimensionality vector representations such that different acoustic …
Analyzing autoencoder-based acoustic word embeddings
Recent studies have introduced methods for learning acoustic word embeddings (AWEs)---
fixed-size vector representations of words which encode their acoustic features. Despite the …
fixed-size vector representations of words which encode their acoustic features. Despite the …
Multilingual jointly trained acoustic and written word embeddings
Acoustic word embeddings (AWEs) are vector representations of spoken word segments.
AWEs can be learned jointly with embeddings of character sequences, to generate …
AWEs can be learned jointly with embeddings of character sequences, to generate …