Speech recognition has become common in many application domains. Incorporating acoustic-phonetic knowledge into Automatic Speech Recognition (ASR) systems design has been proven a viable approach to rise ASR accuracy. Manner of articulation attributes such as vowel, stop, fricative, approximant, nasal, and silence are examples of such knowledge. Neural networks have already been used successfully as detectors for manner of articulation attributes starting from representations of speech signal frames. In this paper, a set of six detectors for the above mentioned attributes is designed based on the E-αNet model of neural networks. This model was chosen for its capability to learn hidden activation functions that results in better generalization properties. Experimental set-up and results are presented that show an average 3.5% improvement over a baseline neural network implementation.
|Titolo della pubblicazione ospite||Neural nets : 16th Italian workshop on neural nets, WIRN 2005 and International workshop on natural and artificial immune systems, NAIS 2005 Vietri sul mare, Italy, June 8-11, 2005 : revised selected papers|
|Numero di pagine||7|
|Stato di pubblicazione||Published - 2005|
|Nome||LECTURE NOTES IN COMPUTER SCIENCE|