Abstract | ||
---|---|---|
In this paper we describe the design of a phoneme classifier that is based on AIDA, a speech database that has been recently proposed as a standard for Italian concerning the phonetic level. We present experimental results using LVQ and show that the proper selection of Kohonen's learning parameter α, based on some intriguing links with Backpropagation learning, contributes to improve the performance with respect to standard heuristics proposed in the literature [Konen, Proc. IEEE 78 (9) (1990) 1464–1480]. |
Year | DOI | Venue |
---|---|---|
2000 | 10.1016/S0925-2312(00)00312-X | Neurocomputing |
Keywords | Field | DocType |
Automatic speech recognition,Backpropagation,Competitive radial basis functions,Learning vector quantization,Phone classification,Radial basis functions | Radial basis function network,Radial basis function,Computer science,Learning vector quantization,Self-organizing map,Heuristics,Phone,Artificial intelligence,Backpropagation,Machine learning | Journal |
Volume | Issue | ISSN |
34 | 1-4 | 0925-2312 |
Citations | PageRank | References |
4 | 0.43 | 14 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Piero Cosi | 1 | 224 | 43.27 |
Paolo Frasconi | 2 | 2984 | 368.70 |
Marco Gori | 3 | 839 | 83.06 |
luca lastrucci | 4 | 4 | 0.43 |
Giovanni Soda | 5 | 957 | 174.35 |