Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Arisoy, A."'
Autor:
Ebru Arisoy, Enver Fakhan
Publikováno v:
2020 28th Signal Processing and Communications Applications Conference (SIU).
Publikováno v:
SIU
Subword units are often utilized to achieve better performance in speech recognition because of the high number of observed words in agglutinative languages. In this study, the proper use of subword units is explored in recognition by a reconsiderati
Autor:
Ebru Arisoy, Murat Saraglar
Publikováno v:
SIU
In this study a decade old automatic speech recognition system for Turkish broadcast news transcription is revisited and updated with the latest methods. Recently deep learning using artificial neural networks resulted in significant improvements in
Autor:
Ünal Dikmen, Muzaffer Özgü Arisoy
Publikováno v:
GEOPHYSICS. 80:J7-J17
Edge enhancement and detection techniques are fundamental operations in magnetic data interpretation. Many techniques for edge enhancement have been developed, some based on profile data and others designed for grid-based data sets. Methods that are
Autor:
Ebru Arisoy
Publikováno v:
SIU
With the increase of online video lectures, using speech and language processing technologies for education has become quite important. This paper presents an automatic transcription and retrieval system developed for processing spoken lectures in Tu
Publikováno v:
IEEE Transactions on Audio, Speech, and Language Processing. 17:874-883
This paper summarizes our recent efforts for building a Turkish Broadcast News transcription and retrieval system. The agglutinative nature of Turkish leads to a high number of out-of-vocabulary (OOV) words which in turn lower automatic speech recogn
Autor:
Ebru Arisoy, Murat Saraclar, Matti Varjokallio, Mikko Kurimo, Mathias Creutz, Andreas Stolcke, Teemu Hirsimäki, Antti Puurula, Vesa Siivola, Janne Pylkkönen
Publikováno v:
ACM Transactions on Speech and Language Processing. 5:1-29
We explore the use of morph-based language models in large-vocabulary continuous-speech recognition systems across four so-called morphologically rich languages: Finnish, Estonian, Turkish, and Egyptian Colloquial Arabic. The morphs are subword units
Publikováno v:
ICASSP
Model M, an exponential class-based language model, and neural network language models (NNLM's) have outperformed word n-gram language models over a wide range of tasks. However, these gains come at the cost of vastly increased computation when calcu
Publikováno v:
ICASSP
Recurrent neural network language models have enjoyed great success in speech recognition, partially due to their ability to model longer-distance context than word n-gram models. In recurrent neural networks (RNNs), contextual information from past
Publikováno v:
Speech and Computer ISBN: 9783319231310
SPECOM
SPECOM
This paper summarizes the research on discriminative language modeling focusing on its application to automatic speech recognition (ASR). A discriminative language model (DLM) is typically a linear or log-linear model consisting of a weight vector as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e5293084ef176096b1e6f2aaa9807dd
https://doi.org/10.1007/978-3-319-23132-7_2
https://doi.org/10.1007/978-3-319-23132-7_2