In this work, we investigate the problem of speaker independent acoustic-to-articulatory inversion (AAI) in noisy condition within the deep neural network (DNN) framework. We claim that DNN vector-to-vector regression for speech enhancement (DNN-SE) can play a key role in AAI when used in a front-end stage to enhance speech features before AAI back-end processing. Our claim contrasts recent literature reporting a drop in AAI accuracy on MMSE enhanced data and thereby sheds some light on the opportunities offered by DNN-SE in robust speech applications. We have also tested single- and multi-task training strategies of the DNN-SE block and experimentally found the latter to be beneficial to AAI. Moreover, DNN-SE coupled with an AAI deep system tested on enhanced speech can outperform a multi-condition AAI deep system tested on noisy speech. We assess our approach on the Haskins corpus using the Pearson's correlation coefficient (PCC). A 15% relative PCC improvement is observed over a multi-condition AAI system at 0dB signal-to-noise ratio (SNR). Our approach also compares favorably against using a conventional DSP approach, namely MMSE with IMCRA, in the front-end stage.

Shahrebabaki, A.S., Siniscalchi, S.M., Salvi, G., Svendsen, T. (2021). A DNN Based Speech Enhancement Approach to Noise Robust Acoustic-to-Articulatory Inversion. In 53rd IEEE International Symposium on Circuits and Systems (pp. 1-5). IEEE [10.1109/ISCAS51556.2021.9401290].

A DNN Based Speech Enhancement Approach to Noise Robust Acoustic-to-Articulatory Inversion

Siniscalchi, Sabato Marco;
2021-01-01

Abstract

In this work, we investigate the problem of speaker independent acoustic-to-articulatory inversion (AAI) in noisy condition within the deep neural network (DNN) framework. We claim that DNN vector-to-vector regression for speech enhancement (DNN-SE) can play a key role in AAI when used in a front-end stage to enhance speech features before AAI back-end processing. Our claim contrasts recent literature reporting a drop in AAI accuracy on MMSE enhanced data and thereby sheds some light on the opportunities offered by DNN-SE in robust speech applications. We have also tested single- and multi-task training strategies of the DNN-SE block and experimentally found the latter to be beneficial to AAI. Moreover, DNN-SE coupled with an AAI deep system tested on enhanced speech can outperform a multi-condition AAI deep system tested on noisy speech. We assess our approach on the Haskins corpus using the Pearson's correlation coefficient (PCC). A 15% relative PCC improvement is observed over a multi-condition AAI system at 0dB signal-to-noise ratio (SNR). Our approach also compares favorably against using a conventional DSP approach, namely MMSE with IMCRA, in the front-end stage.
2021
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
978-1-7281-9201-7
Shahrebabaki, A.S., Siniscalchi, S.M., Salvi, G., Svendsen, T. (2021). A DNN Based Speech Enhancement Approach to Noise Robust Acoustic-to-Articulatory Inversion. In 53rd IEEE International Symposium on Circuits and Systems (pp. 1-5). IEEE [10.1109/ISCAS51556.2021.9401290].
File in questo prodotto:
File Dimensione Formato  
shahrebabaki2021.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 2.18 MB
Formato Adobe PDF
2.18 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/636670
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact