Invariant Features and Enhanced Speaker Normalization for Automatic Speech Recognition
247 pages, year of publication: 2013
price: 40.50 EUR
Spracherkennung, invariante Merkmalextraktion, Normalisierung
Automatic speech recognition systems have to handle various kinds of variabilities sufficiently well in order to achieve high recognition rates in practice. One of the variabilities that has a major impact on the performance is the vocal tract length of the speakers. Normalization of the features and adaptation of the acoustic models are commonly used methods in speech recognition systems. In contrast to that, a third approach follows the idea of extracting features with transforms that are invariant to vocal tract lengths changes.
This work presents several approaches for extracting invariant features for automatic speech recognition systems. The robustness of these features under various training-test conditions is evaluated and it is described how the robustness of the features to noise can be increased. Furthermore, it is shown how the spectral effects due to different vocal tract lengths can be estimated with a registration method and how this can be used for speaker normalization.
|print:||38.00 EUR ||
||eBundle*: ||48.00 EUR||
For multi-user or campus licences (MyLibrary) please fill in the form or write an email to firstname.lastname@example.org
*You can purchase the eBook (PDF) alone or combined with the printed book (eBundle). In both cases we use the payment service of PayPal for charging you - nevertheless it is not necessary to have a PayPal-account. With purchasing the eBook or eBundle you accept our licence for eBooks.
Wollen auch Sie Ihre Dissertation veröffentlichen?