Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers


This paper introduces Timers and Such, a new open source dataset of spoken English commands for common voice control use cases involving numbers. We describe the gap in existing spoken language understanding datasets that Timers and Such fills, the design and creation of the dataset, and experiments with a number of ASR-based and end-to-end baseline models, the code for which has been made available as part of the SpeechBrain toolkit.

Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 pre-proceedings (NeurIPS Datasets and Benchmarks 2021)