Automatic speech recognition is becoming increasingly more important, with commercial applications such as call steering, dictation or voice-enabled personal assistance systems. Although successful in many respects, the performance of such systems can significantly degrade in noisy environment such as a crowded restaurant. This is due to the fact that noise introduces a mismatch between the clean speech features, which the ASR system has been trained with, and the noisy speech features that are encountered in the operational environment. This dissertation tries to mitigate the degradation in performance using two principally different approaches: speech feature enhancement (SFE) techniques, which minimize the mismatch between clean and nois...
Audio mining systems automatically analyse large amounts of heterogeneous media files such as televi...
Ankara : Department of Electrical and Electronics Engineering and the Institute of Engineering and S...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...
Automatic speech recognition is becoming increasingly more important, with commercial applications s...
Mit der zunehmenden Nutzung und Verbreitung von automatischen Spracherkennungssystemen steigen auch ...
In vielen Anwendungen treten Sprachsignale oft in gestörter Form auf, wie zum Beispiel bei Freisprec...
The first part of this thesis is devoted to the evaluation of approaches which exploit the inherent ...
State-of-the-art automatic speech recognition (ASR) systems can achieve very low word error rates (W...
The automatic speech recognition systems have become a part of our daily lives. People often rely o...
Distant Speech Recognition is motivated by several applications, such as handsfree devices, and conf...
Bei der Verwendung von Freisprechsystemen zur automatischen Spracherkennung tritt das Problem auf, d...
Real world applications such as hands-free dialling in cars may have to perform recognition of spoke...
Imagining everyday life without mobile telephony is nowadays hardly possible. Calls are being made i...
Oggigiorno l’interazione uomo-macchina ha un ruolo fondamentale nella vita quotidiana delle persone....
Colloque avec actes et comité de lecture. internationale.International audienceWe present a novel no...
Audio mining systems automatically analyse large amounts of heterogeneous media files such as televi...
Ankara : Department of Electrical and Electronics Engineering and the Institute of Engineering and S...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...
Automatic speech recognition is becoming increasingly more important, with commercial applications s...
Mit der zunehmenden Nutzung und Verbreitung von automatischen Spracherkennungssystemen steigen auch ...
In vielen Anwendungen treten Sprachsignale oft in gestörter Form auf, wie zum Beispiel bei Freisprec...
The first part of this thesis is devoted to the evaluation of approaches which exploit the inherent ...
State-of-the-art automatic speech recognition (ASR) systems can achieve very low word error rates (W...
The automatic speech recognition systems have become a part of our daily lives. People often rely o...
Distant Speech Recognition is motivated by several applications, such as handsfree devices, and conf...
Bei der Verwendung von Freisprechsystemen zur automatischen Spracherkennung tritt das Problem auf, d...
Real world applications such as hands-free dialling in cars may have to perform recognition of spoke...
Imagining everyday life without mobile telephony is nowadays hardly possible. Calls are being made i...
Oggigiorno l’interazione uomo-macchina ha un ruolo fondamentale nella vita quotidiana delle persone....
Colloque avec actes et comité de lecture. internationale.International audienceWe present a novel no...
Audio mining systems automatically analyse large amounts of heterogeneous media files such as televi...
Ankara : Department of Electrical and Electronics Engineering and the Institute of Engineering and S...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...