On Architectures and Training for Raw Waveform Feature Extraction in ASR
IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 267–274
Abstract
With the success of neural network based modeling in auto-matic speech recognition (ASR), many studies investigated acoustic modeling and learning of feature extractors directly based on the raw waveform. Recently, one line of research has focused on unsupervised pre-training of feature extractors on audio-only data to improve downstream ASR performance. In this work, we investigate the usefulness of one of these front-end frameworks, namely wav2vec, in a setting without additional untranscribed data for hybrid ASR systems. We compare this framework both to the manually defined stan-dard Gammatone feature set, as well as to features extracted as part of the acoustic model of an ASR system trained su-pervised. We study the benefits of using the pre-trained feature extractor and explore how to additionally exploit an ex-isting acoustic model trained with different features. Finally, we systematically examine combinations of the described features in order to further advance the performance.
Authors 4
-
Affiliation as printed
Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074
-
Affiliation as printed
Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074
-
Affiliation as printed
Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074
-
Affiliation as printed
Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074
Cited by 3 stored of 3
3 results
No patents citing this paper on Lens.org (checked 2026-10-06).