Conventional keyword search systems operate on automatic speech recognit...
End-to-end speech recognition models are improved by incorporating exter...
Improving end-to-end speech recognition by incorporating external text d...
Recently, neural approaches to spoken content retrieval have become popu...
When documenting oral-languages, Unsupervised Word Segmentation (UWS) fr...
In this work, we propose a hierarchical subspace model for acoustic unit...
In this paper we describe our submission to the Zerospeech 2020 challeng...