Autoregressive Parameter Estimation with DNN-based Pre-processing

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

114 Downloads (Pure)

Abstract

In this paper, a method for estimating the autoregressive parameters from a signal segment is proposed. The method is based on a deep neural network (DNN) in combination with the classical Levinson-Durbin recursion (LDR). The DNN acts as a pre-processor for the LDR and can be trained on different metrics commonly encountered in speech processing using a generalized analysis-by-synthesis (GABS) structure where the LDR acts as the encoder. Unlike end-to-end data-driven approaches, this structure ensures that the DNN is easy to train and initialize since the DNN only has to learn a simple mapping. The results confirm this and show that the proposed method produces an AR-spectrum that efficiently represents the speech spectrum in terms of the Itakura-Saito divergence, Kullback-Leibler divergence, log-spectral distortion, and speech distortion.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Acousics, Speech, and Signal Processing
PublisherIEEE
Publication dateMay 2020
DOIs
Publication statusPublished - May 2020
SeriesProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN1520-6149

Fingerprint Dive into the research topics of 'Autoregressive Parameter Estimation with DNN-based Pre-processing'. Together they form a unique fingerprint.

  • Cite this

    Cui, Z., Bao, C., Nielsen, J. K., & Christensen, M. G. (2020). Autoregressive Parameter Estimation with DNN-based Pre-processing. In Proceedings of the International Conference on Acousics, Speech, and Signal Processing IEEE. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing https://doi.org/10.1109/ICASSP40776.2020.9053755