Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers
arXiv:2104.01604
Abstract
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.
arXiv commentAccepted to NeurIPS 2021 - Datasets and Benchmarks Track
References in corpus (6)
- Attention-Based Models for Speech Recognition
- Sequence Transduction with Recurrent Neural Networks
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- SpeechBrain: A General-Purpose Speech Toolkit
- Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning
- A Streaming End-to-End Framework For Spoken Language Understanding