Applying the Generalized Dombi Operator Family to the Speech Recognition Task
|
| Title | Applying the Generalized Dombi Operator Family to the Speech Recognition Task |
| Authors | |
| Abstract | In the automatic speech recognition (ASR) problem, the task of constructing one word- or sentence-level probability from the available phoneme-level probabilities is a very important one. Here we try to improve the performance of ASR systems by applying operators taken from fuzzy logic which have the sort of properties this problem requires. In this paper we do this by using the Generalized Dombi Operator, which, by its two adjustable parameters and incorporating other well-known fuzzy operators, seems quite suitable. To properly adjust these parameters, we used the public optimization package called Snobfit. The results show that our approach is surprisingly successful: we were able to reduce the overall error rate by 53.4%. |
| Publisher | University of Zagreb, University Computing Centre - SRCE |
| Date | 1970-01-01 |
| Source | Journal of Computing and Information Technology Vol 17, No 3 (2009) |
| Rights | CIT. Journal of Computing and Information Technology is an open access journal.Authors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work´s authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal´s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access). |