Exploració per tema "Automatic Speech Recognition"
Ara es mostren els items 1-3 de 3
-
Automatic speech recognition with deep neural networks for impaired speech
(Springer, 2016)
Text en actes de congrés
Accés obertAutomatic Speech Recognition has reached almost human performance in some controlled scenarios. However, recognition of impaired speech is a difficult task for two main reasons: data is (i) scarce and (ii) heterogeneous. ... -
Efficient transformers for direct speech translation
(Universitat Politècnica de Catalunya, 2021-07)
Treball Final de Grau
Accés obertIn this thesis, we propose a new approach for Speech-to-Text translation, where thanks to an efficient Transformer we can work with a spectrogram without having to use convolutional layers before the Transformer. This ... -
Recurrent Neural Networks for Speaker Dependent Language Modeling
(Universitat Politècnica de Catalunya, 2014-08)
Projecte/Treball Final de Carrera
Accés obert[ANGLÈS] This work focuses on building and testing statistical language models based on recurrent neural networks. Although both speaker independent and dependent language models will be discussed and compared, this thesis ...