Correlation distance skip connection denoising autoencoder (CDSK-DAE) for speech feature enhancement

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise robust end-to-end ASR system by introducing a novel variant of...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Applied acoustics Jg. 163; S. 107213
Hauptverfasser:	Badi, Alzahra, Park, Sangwook, Han, David K., Ko, Hanseok
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.06.2020
Schlagworte:	Automatic speech recognition (ASR) Correlation distance measure (CDM) Skip connection Denoising Autoencoder (SK-DAE) Automatic speech recognition (ASR) Skip connection Denoising Autoencoder (SK-DAE) Correlation distance measure (CDM)
ISSN:	0003-682X, 1872-910X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise robust end-to-end ASR system by introducing a novel variant of denoising autoencoder (DAE). The proposed method uses skip connections in both encoder and decoder sides by passing speech information of the target frame from input to the model. It also uses a new objective function in training model that uses a correlation distance measure in penalty terms by measuring dependency of the latent target features and the model (latent features and enhanced features obtained from the DAE). Performance of the proposed method was compared against a conventional model and a state of the art model under both seen and unseen noisy environments of 7 different types of background noise with different SNR levels (0, 5, 10 and 20 dB). The proposed method also is tested using linear and non-linear penalty terms as well, where, they both show an improvement on the overall average WER under noisy conditions both seen and unseen in comparison to the state-of-the-art model.
ISSN:	0003-682X 1872-910X
DOI:	10.1016/j.apacoust.2020.107213