Energy-Efficient Speaker Identification with Low-Precision Networks
Power-consumption in small devices is dominated by off-chip memory accesses, necessitating small models that can fit in on-chip memory. In the task of text-dependent speaker identification, we demonstrate a 16x byte-size reduction for state-of-art small-footprint LCN/CNN/DNN speaker identification m...
Autori principali: | , , |
---|---|
Altri autori: | |
Natura: | Articolo |
Lingua: | English |
Pubblicazione: |
Institute of Electrical and Electronics Engineers (IEEE)
2019
|
Accesso online: | https://hdl.handle.net/1721.1/121168 |