On Optimal Filtering for Speech Decomposition

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

1 Citation (Scopus)
26 Downloads (Pure)

Abstract

Optimal linear filtering has been used extensively for speech enhancement. In this paper, we take a first step in trying to apply linear filtering to the decomposition of a noisy speech signal into its components. The problem of decomposing speech into its voiced and unvoiced components is considered as an estimation problem. Assuming a harmonic model for the voiced speech, we propose a Wiener filtering scheme which estimates both components separately in the presence of noise. It is shown under which conditions this optimal filtering formulation outperforms two state-of-the-art speech decomposition methods, which is also revealed by objective measures, spectrograms and informal listening tests.
Original languageEnglish
Title of host publication2018 26th European Signal Processing Conference (EUSIPCO)
Number of pages5
PublisherIEEE
Publication date2018
Pages2325-2329
ISBN (Print)978-90-827970-0-8, 978-1-5386-3736-4
ISBN (Electronic)978-9-0827-9701-5
DOIs
Publication statusPublished - 2018
Event26th European Signal Processing Conference - Rome, Italy
Duration: 3 Sep 20187 Sep 2018
Conference number: 26
http://www.eusipco2018.org

Conference

Conference26th European Signal Processing Conference
Number26
CountryItaly
CityRome
Period03/09/201807/09/2018
Internet address
SeriesProc. European Signal Processing Conference
ISSN2076-1465

Fingerprint

Decomposition
Speech enhancement

Keywords

  • speech decomposition
  • time-domain filtering
  • Wiener filter
  • voiced speech
  • unvoiced speech

Cite this

Esquivel Jaramillo, A., Nielsen, J. K., & Christensen, M. G. (2018). On Optimal Filtering for Speech Decomposition. In 2018 26th European Signal Processing Conference (EUSIPCO) (pp. 2325-2329). IEEE. Proc. European Signal Processing Conference https://doi.org/10.23919/EUSIPCO.2018.8553512
Esquivel Jaramillo, Alfredo ; Nielsen, Jesper Kjær ; Christensen, Mads Græsbøll. / On Optimal Filtering for Speech Decomposition. 2018 26th European Signal Processing Conference (EUSIPCO). IEEE, 2018. pp. 2325-2329 (Proc. European Signal Processing Conference).
@inproceedings{20289dfb3b134bd0837b520ad6003366,
title = "On Optimal Filtering for Speech Decomposition",
abstract = "Optimal linear filtering has been used extensively for speech enhancement. In this paper, we take a first step in trying to apply linear filtering to the decomposition of a noisy speech signal into its components. The problem of decomposing speech into its voiced and unvoiced components is considered as an estimation problem. Assuming a harmonic model for the voiced speech, we propose a Wiener filtering scheme which estimates both components separately in the presence of noise. It is shown under which conditions this optimal filtering formulation outperforms two state-of-the-art speech decomposition methods, which is also revealed by objective measures, spectrograms and informal listening tests.",
keywords = "speech decomposition, time-domain filtering, Wiener filter, voiced speech, unvoiced speech",
author = "{Esquivel Jaramillo}, Alfredo and Nielsen, {Jesper Kj{\ae}r} and Christensen, {Mads Gr{\ae}sb{\o}ll}",
year = "2018",
doi = "10.23919/EUSIPCO.2018.8553512",
language = "English",
isbn = "978-90-827970-0-8",
series = "Proc. European Signal Processing Conference",
publisher = "IEEE",
pages = "2325--2329",
booktitle = "2018 26th European Signal Processing Conference (EUSIPCO)",
address = "United States",

}

Esquivel Jaramillo, A, Nielsen, JK & Christensen, MG 2018, On Optimal Filtering for Speech Decomposition. in 2018 26th European Signal Processing Conference (EUSIPCO). IEEE, Proc. European Signal Processing Conference, pp. 2325-2329, 26th European Signal Processing Conference, Rome, Italy, 03/09/2018. https://doi.org/10.23919/EUSIPCO.2018.8553512

On Optimal Filtering for Speech Decomposition. / Esquivel Jaramillo, Alfredo ; Nielsen, Jesper Kjær; Christensen, Mads Græsbøll.

2018 26th European Signal Processing Conference (EUSIPCO). IEEE, 2018. p. 2325-2329 (Proc. European Signal Processing Conference).

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

TY - GEN

T1 - On Optimal Filtering for Speech Decomposition

AU - Esquivel Jaramillo, Alfredo

AU - Nielsen, Jesper Kjær

AU - Christensen, Mads Græsbøll

PY - 2018

Y1 - 2018

N2 - Optimal linear filtering has been used extensively for speech enhancement. In this paper, we take a first step in trying to apply linear filtering to the decomposition of a noisy speech signal into its components. The problem of decomposing speech into its voiced and unvoiced components is considered as an estimation problem. Assuming a harmonic model for the voiced speech, we propose a Wiener filtering scheme which estimates both components separately in the presence of noise. It is shown under which conditions this optimal filtering formulation outperforms two state-of-the-art speech decomposition methods, which is also revealed by objective measures, spectrograms and informal listening tests.

AB - Optimal linear filtering has been used extensively for speech enhancement. In this paper, we take a first step in trying to apply linear filtering to the decomposition of a noisy speech signal into its components. The problem of decomposing speech into its voiced and unvoiced components is considered as an estimation problem. Assuming a harmonic model for the voiced speech, we propose a Wiener filtering scheme which estimates both components separately in the presence of noise. It is shown under which conditions this optimal filtering formulation outperforms two state-of-the-art speech decomposition methods, which is also revealed by objective measures, spectrograms and informal listening tests.

KW - speech decomposition

KW - time-domain filtering

KW - Wiener filter

KW - voiced speech

KW - unvoiced speech

U2 - 10.23919/EUSIPCO.2018.8553512

DO - 10.23919/EUSIPCO.2018.8553512

M3 - Article in proceeding

SN - 978-90-827970-0-8

SN - 978-1-5386-3736-4

T3 - Proc. European Signal Processing Conference

SP - 2325

EP - 2329

BT - 2018 26th European Signal Processing Conference (EUSIPCO)

PB - IEEE

ER -

Esquivel Jaramillo A, Nielsen JK, Christensen MG. On Optimal Filtering for Speech Decomposition. In 2018 26th European Signal Processing Conference (EUSIPCO). IEEE. 2018. p. 2325-2329. (Proc. European Signal Processing Conference). https://doi.org/10.23919/EUSIPCO.2018.8553512