Robustness of end-to-end Automatic Speech Recognition Models – A Case Study using Mozilla DeepSpeech

no code implementations • KONVENS (WS) 2021 • Aashish Agarwal, Torsten Zesch

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Towards Real-World Streaming Speech Translation for Code-Switched Speech

1 code implementation • 19 Oct 2023 • Belen Alastruey, Matthias Sperber, Christian Gollan, Dominic Telaar, Tim Ng, Aashish Agarwal

Code-switching (CS), i. e. mixing different languages in a single sentence, is a common phenomenon in communication and can be challenging in many Natural Language Processing (NLP) settings.

Sentence Translation

Dialectal Speech Recognition and Translation of Swiss German Speech to Standard German Text: Microsoft's Submission to SwissText 2021

no code implementations • 15 Jun 2021 • Yuriy Arabskyy, Aashish Agarwal, Subhadeep Dey, Oscar Koller

This paper describes the winning approach in the Shared Task 3 at SwissText 2021 on Swiss German Speech to Standard German Text, a public competition on dialect recognition and translation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Robustness of end-to-end Automatic Speech Recognition Models -- A Case Study using Mozilla DeepSpeech

no code implementations • 8 May 2021 • Aashish Agarwal, Torsten Zesch

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2