Abstract | ||
---|---|---|
The robustness and consistency of sensory inference models under changing environmental conditions and hardware is a crucial requirement for the generalizability of recent innovative work, particularly in the field of deep learning, from the lab to the real world. We measure the extent to which current speech recognition cloud models are robust to background noise, and show that hardware variability is still a problem for real-world applicability of state-of-the-art speech recognition models.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3267305.3267505 | UbiComp '18: The 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Singapore
Singapore
October, 2018 |
Keywords | Field | DocType |
Audio Sensing, Machine Learning, Robustness, ASR | Generalizability theory,Background noise,Computer science,Inference,Audio sensing,Speech recognition,Robustness (computer science),Human–computer interaction,Artificial intelligence,Deep learning,Cloud computing | Conference |
ISBN | Citations | PageRank |
978-1-4503-5966-5 | 1 | 0.34 |
References | Authors | |
13 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Akhil Mathur | 1 | 145 | 15.21 |
Anton Isopoussu | 2 | 2 | 2.08 |
Fahim Kawsar | 3 | 909 | 80.24 |
Robert Smith | 4 | 1 | 0.34 |
Nicholas D. Lane | 5 | 4247 | 248.15 |
Nadia Berthouze | 6 | 123 | 14.38 |