2000 Presentations (Communicative Events)
Tandem acoustic modeling: Neural nets for mainstream ASR?
A discussion of the "Tandem modeling" approach, i.e. feeding neural network outputs as features into HTK to do better than either approach alone.
- shef-tandem-2000-06.pdf application/pdf 222 KB Download File
More About This Work
- Academic Units
- Electrical Engineering
- Published Here
- July 18, 2012
Presented at the Sheffield University Speech and Hearing Group, June 20, 2000.