Loading...
Please wait, while we are loading the content...
Similar Documents
Chapter 11 – Summary and future directions
| Content Provider | Semantic Scholar |
|---|---|
| Author | Li, Jinyu |
| Copyright Year | 2016 |
| Abstract | In this book, we presented robust ASR techniques guided by a unified mathematical framework. To offer insight into the distinct capabilities of these techniques and their connections, we have used a taxonomy-oriented approach with five key attributes: feature vs. model domain processing, explicit vs. implicit distortion modeling, use vs. absence of prior knowledge about the distortion, deterministic vs. uncertainty processing, and joint vs. disjoint training, to organize the vast amount of material and to demonstrate the commonalities and differences among the plethora of robust ASR methods presented in this book. The representative technologies for both GMMs and DNNs are described. Given the recent trend that DNNs become the most popular modeling technologies in ASR, the challenges and future research directions are discussed. |
| Starting Page | 261 |
| Ending Page | 280 |
| Page Count | 20 |
| File Format | PDF HTM / HTML |
| DOI | 10.1016/B978-0-12-802398-3.00011-8 |
| Alternate Webpage(s) | http://shodhganga.inflibnet.ac.in:8080/jspui/bitstream/10603/186532/17/17_chapter%2011.pdf |
| Alternate Webpage(s) | https://doi.org/10.1016/B978-0-12-802398-3.00011-8 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Chapter |
