The CHiME challenges have played a significant role in the development a...
We introduce HK-LegiCoST, a new three-way parallel corpus of
Cantonese-E...
This paper presents a novel algorithm for building an automatic speech
r...
In this work, we seek to build effective code-switched (CS) automatic sp...
Self-supervised model pre-training has recently garnered significant
int...
We present the Multilingual TEDx corpus, built to support speech recogni...
A major hurdle in data-driven research on typology is having sufficient ...
We investigate the problem of searching for a lexeme-set in speech by
se...
We report on adaptation of multilingual end-to-end speech recognition mo...
We explore training attention-based encoder-decoder ASR for low-resource...
This paper investigates the applications of various multilingual approac...
Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...
In topic identification (topic ID) on real-world unstructured audio, an ...
This paper introduces a new open source platform for end-to-end speech
p...
We present a new end-to-end architecture for automatic speech recognitio...
We describe the system our team used during NIST's LoReHLT (Low Resource...
Modern topic identification (topic ID) systems for speech use automatic
...