Add to ORKGIn this study, techniques for classification with missing or unreliable data are applied to the problem of noise-robustness in Automatic Speech Recognition (ASR). The techniques de-scribed make minimal assumptions about any noise background and rely instead on what is known about clean speech. A sys-tem is evaluated using the Aurora 2 connected digit recognition task. Using models trained on clean speech we obtain a 65% relative improvement over the Aurora clean training baseline system, a performance comparable with the Aurora baseline for multicondition training. 1
Much research has been focused on the problem of achieving automatic speech recognition (ASR) which ...
Maintaining a high level of robustness for Automatic Speech Recognition (ASR) systems is especially ...
Motivated by the human ability to maintain a high level of speech recognition when large parts of th...
Automatic speech recognition (ASR) systems have made dramatic performance leaps in the recent past. ...
Human speech perception is robust in the face of a wide variety of distortions, both experimentally ...
This report presents a review of the main research directions in noise robust automatic speech recog...
Much research has been focused on the problem of achieving automatic speech recognition (ASR) which ...
In the missing data approach to robust Automatic Speech Recognition (ASR), time-frequency regions wh...
The mismatch between system training and operat-ing conditions often has negative influences on auto...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Current automatic speech recognisers rely for a great deal on statistical models learned from traini...
Automatic speech recognition (ASR) is a fascinating field of science where the machine almost become...
This paper deals with the analysis of Automatic Speech Recognition (ASR) suitable for usage within n...
Although the field of automatic speaker recognition (ASR) has been the subject of extensive research...
Missing Data Theory (MDT) has shown to improve the robustness of automatic speech recognition (ASR) ...
Much research has been focused on the problem of achieving automatic speech recognition (ASR) which ...
Maintaining a high level of robustness for Automatic Speech Recognition (ASR) systems is especially ...
Motivated by the human ability to maintain a high level of speech recognition when large parts of th...
Automatic speech recognition (ASR) systems have made dramatic performance leaps in the recent past. ...
Human speech perception is robust in the face of a wide variety of distortions, both experimentally ...
This report presents a review of the main research directions in noise robust automatic speech recog...
Much research has been focused on the problem of achieving automatic speech recognition (ASR) which ...
In the missing data approach to robust Automatic Speech Recognition (ASR), time-frequency regions wh...
The mismatch between system training and operat-ing conditions often has negative influences on auto...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Current automatic speech recognisers rely for a great deal on statistical models learned from traini...
Automatic speech recognition (ASR) is a fascinating field of science where the machine almost become...
This paper deals with the analysis of Automatic Speech Recognition (ASR) suitable for usage within n...
Although the field of automatic speaker recognition (ASR) has been the subject of extensive research...
Missing Data Theory (MDT) has shown to improve the robustness of automatic speech recognition (ASR) ...
Much research has been focused on the problem of achieving automatic speech recognition (ASR) which ...
Maintaining a high level of robustness for Automatic Speech Recognition (ASR) systems is especially ...
Motivated by the human ability to maintain a high level of speech recognition when large parts of th...