Abstract
A memristor-based pattern-matching circuit for realising a hardware oriented approach to isolated speech word recognition is introduced. As distinct from algorithmic solutions, the approach takes advantage of the memristor to memorise and match speech templates in a fast, parallel, low-power and scalable architecture. When tested for isolated word recognition by simulations on the benchmark (TIMIT) and Massachusetts Institute of Technology database, recognition accuracies of 94.5% on clean words and 88% on words with a SNR of 5 dB were achieved.
| Original language | English |
|---|---|
| Pages (from-to) | 1370-1372 |
| Number of pages | 3 |
| Journal | Electronics Letters |
| Volume | 51 |
| Issue number | 17 |
| DOIs | |
| Publication status | Published - Aug 20 2015 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
Cite this
Memristor pattern recogniser : Isolated speech word recognition. / Maan, A. K.; James, A. P.; Dimitrijev, S.
In: Electronics Letters, Vol. 51, No. 17, 20.08.2015, p. 1370-1372.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Memristor pattern recogniser
T2 - Isolated speech word recognition
AU - Maan, A. K.
AU - James, A. P.
AU - Dimitrijev, S.
PY - 2015/8/20
Y1 - 2015/8/20
N2 - A memristor-based pattern-matching circuit for realising a hardware oriented approach to isolated speech word recognition is introduced. As distinct from algorithmic solutions, the approach takes advantage of the memristor to memorise and match speech templates in a fast, parallel, low-power and scalable architecture. When tested for isolated word recognition by simulations on the benchmark (TIMIT) and Massachusetts Institute of Technology database, recognition accuracies of 94.5% on clean words and 88% on words with a SNR of 5 dB were achieved.
AB - A memristor-based pattern-matching circuit for realising a hardware oriented approach to isolated speech word recognition is introduced. As distinct from algorithmic solutions, the approach takes advantage of the memristor to memorise and match speech templates in a fast, parallel, low-power and scalable architecture. When tested for isolated word recognition by simulations on the benchmark (TIMIT) and Massachusetts Institute of Technology database, recognition accuracies of 94.5% on clean words and 88% on words with a SNR of 5 dB were achieved.
UR - http://www.scopus.com/inward/record.url?scp=84939175114&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84939175114&partnerID=8YFLogxK
U2 - 10.1049/el.2015.1428
DO - 10.1049/el.2015.1428
M3 - Article
VL - 51
SP - 1370
EP - 1372
JO - Electronics Letters
JF - Electronics Letters
SN - 0013-5194
IS - 17
ER -