@InProceedings{Wagner2023_1185,
author = {Dominik Wagner and Sebastian P. Bayerl and Tobias Bocklet},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2023},
title = {Implementing Easy-to-Use Recipes for the Switchboard Benchmark},
year = {2023},
editor = {Christoph Draxler},
month = mar,
pages = {150--157},
publisher = {TUDpress, Dresden},
abstract = {We report on our contribution of templates for tokenization, language
modeling, and automatic speech recognition (ASR) on the Switchboard benchmark
to the open-source general-purpose toolkit SpeechBrain. Three recipes for the
training of end-to-end ASR systems were implemented. We describe their model
architectures, as well as the necessary data preparation steps. The word error rates
achievable with our models are comparable to or better than those of other popular
toolkits. Pre-trained ASR models were made available on HuggingFace. They can
be easily integrated into research projects or used directly for quick inference via a
hosted inference API.},
isbn = {978-3-95908-303-4},
issn = {0940-6832},
keywords = {Automatic Speech Recognition},
url = {https://www.essv.de/pdf/2023_150_157.pdf},
}