Name
Title | ||
|---|---|---|
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training |
Abstract | ||
|---|---|---|
We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To compensate for data domains that are missing from on-device training caches, we employed joint federated-centralized training. And to learn in the absence of curated labels on-device, we formulated a confidence filtering strategy based on user-feedback signals for federated distillation. These techniques created models that significantly improved quality metrics in offline evaluations and user-experience metrics in live A/B experiments. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.21437/INTERSPEECH.2022-11050 | Conference of the International Speech Communication Association (INTERSPEECH) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 12 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Andrew Hard | 1 | 11 | 0.90 |
| Kurt Partridge | 2 | 20 | 3.80 |
| Neng Chen | 3 | 0 | 0.34 |
| Sean Augenstein | 4 | 0 | 0.68 |
| Aishanee Shah | 5 | 0 | 0.34 |
| Hyun Jin Park | 6 | 1 | 0.68 |
| Alex Park | 7 | 0 | 0.68 |
| Sara Ng | 8 | 0 | 1.01 |
| Jessica Nguyen | 9 | 0 | 0.34 |
| Ignacio Lopez-Moreno | 10 | 187 | 14.97 |
| Rajiv Mathews | 11 | 12 | 5.30 |
| Françoise Beaufays | 12 | 6 | 2.82 |