Abstract
When deployed in embedded systems, speech recognizers are necessarily reduced from large-vocabulary continuous speech recognizers (LVCSR) found on desktops or servers to fit the limited hardware. However, embedded hardware continues to evolve in capability; today's smartphones are vastly more powerful than their recent ancestors. This begets a new question: which hardware features not currently found on today's embedded platforms, but potentially add-ons to tomorrow's devices, are most likely to improve recognition performance? Said differently - what is the sensitivity of the recognizer to fine-grain details of the embedded hardware resources? To answer this question rigorously and quantitatively, we offer results from a detailed study of LVCSR performance as a function of microarchitecture options on an embedded ARM11 and an enterprise-class Intel Core2Duo. We estimate speed and energy consumption, and show, feature by feature, how hardware resources impact recognizer performance.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1923-1926 |
| Number of pages | 4 |
| Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
| State | Published - 2009 |
| Externally published | Yes |
| Event | 10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom Duration: Sep 6 2009 → Sep 10 2009 |
Keywords
- Hardware profiling
- Software performance
- Speech recognition
ASJC Scopus subject areas
- Human-Computer Interaction
- Signal Processing
- Software
- Sensory Systems