H Kamper - ICASSP 2019-2019 IEEE International Conference …, 2019 - ieeexplore.ieee.org
We investigate unsupervised models that can map a variable-duration speech segment to a fixed-dimensional representation. In settings where unlabelled speech is the only available …
Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is …
S Jabeen, X Gao, P Andreae - Artificial Intelligence Review, 2020 - Springer
Semantic association computation is the process of quantifying the strength of a semantic connection between two textual units, based on different types of semantic relations …
Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one …
Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a …
In text, word2vec transforms each word into a fixed-size vector used as the basic component in applications of natural language processing. Given a large collection of unannotated …
As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unified end …
Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W …
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such …