Real-time audio processing for hearing aids using a model-based Bayesian inference framework

Martin Roa-Villescas; A. (Bert) de Vries; Sander Stuijk; Henk Corporaal

doi:10.1145/3378678.3397528

Real-time audio processing for hearing aids using a model-based Bayesian inference framework

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Development of hearing aid (HA) signal processing algorithms entails an iterative process between two design steps, namely algorithm development and the embedded implementation. Algorithm designers favor high-level programming languages for several reasons including higher productivity, code readability and, perhaps most importantly, availability of state-of-the-art signal processing frameworks that open new research directions. Embedded software, on the other hand, is preferably implemented using a low-level programming language to allow finer control of the hardware, an essential trait in real-time processing applications. In this paper we present a technique that allows deploying DSP algorithms written in Julia, a modern high-level programming language, on a real-time HA processing platform known as openMHA. We demonstrate this technique by using a model-based Bayesian inference framework to perform real-time audio processing.

Original language	English
Title of host publication	Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020
Subtitle of host publication	SCOPES 2020
Editors	Sander Stuijk
Publisher	Association for Computing Machinery, Inc.
Pages	82-85
Number of pages	4
ISBN (Electronic)	978-1-4503-7131-5
DOIs	https://doi.org/10.1145/3378678.3397528
Publication status	Published - 25 May 2020

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

audio signal processing
Hearing impairment
Julia
openMHA
real time
digital audio signal processing
hearing aids

Access to Document

10.1145/3378678.3397528Licence: Unspecified

Cite this

Roa-Villescas, M., de Vries, A., Stuijk, S., & Corporaal, H. (2020). Real-time audio processing for hearing aids using a model-based Bayesian inference framework. In S. Stuijk (Ed.), Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020: SCOPES 2020 (pp. 82-85). Association for Computing Machinery, Inc.. https://doi.org/10.1145/3378678.3397528

@inproceedings{7c1f548edccd40d08a7f399e2abbd6fd,

title = "Real-time audio processing for hearing aids using a model-based Bayesian inference framework",

abstract = "Development of hearing aid (HA) signal processing algorithms entails an iterative process between two design steps, namely algorithm development and the embedded implementation. Algorithm designers favor high-level programming languages for several reasons including higher productivity, code readability and, perhaps most importantly, availability of state-of-the-art signal processing frameworks that open new research directions. Embedded software, on the other hand, is preferably implemented using a low-level programming language to allow finer control of the hardware, an essential trait in real-time processing applications. In this paper we present a technique that allows deploying DSP algorithms written in Julia, a modern high-level programming language, on a real-time HA processing platform known as openMHA. We demonstrate this technique by using a model-based Bayesian inference framework to perform real-time audio processing.",

keywords = "audio signal processing, Hearing impairment, Julia, openMHA, real time, digital audio signal processing, hearing aids",

author = "Martin Roa-Villescas and \{de Vries\}, \{A. (Bert)\} and Sander Stuijk and Henk Corporaal",

year = "2020",

month = may,

day = "25",

doi = "10.1145/3378678.3397528",

language = "English",

pages = "82--85",

editor = "Sander Stuijk",

booktitle = "Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020",

publisher = "Association for Computing Machinery, Inc.",

address = "United States",

}

Roa-Villescas, M , de Vries, A , Stuijk, S & Corporaal, H 2020, Real-time audio processing for hearing aids using a model-based Bayesian inference framework. in S Stuijk (ed.), Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020: SCOPES 2020. Association for Computing Machinery, Inc., pp. 82-85. https://doi.org/10.1145/3378678.3397528

Real-time audio processing for hearing aids using a model-based Bayesian inference framework. / Roa-Villescas, Martin ; de Vries, A. (Bert); Stuijk, Sander et al.
Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020: SCOPES 2020. ed. / Sander Stuijk. Association for Computing Machinery, Inc., 2020. p. 82-85.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Real-time audio processing for hearing aids using a model-based Bayesian inference framework

AU - Roa-Villescas, Martin

AU - de Vries, A. (Bert)

AU - Stuijk, Sander

AU - Corporaal, Henk

PY - 2020/5/25

Y1 - 2020/5/25

N2 - Development of hearing aid (HA) signal processing algorithms entails an iterative process between two design steps, namely algorithm development and the embedded implementation. Algorithm designers favor high-level programming languages for several reasons including higher productivity, code readability and, perhaps most importantly, availability of state-of-the-art signal processing frameworks that open new research directions. Embedded software, on the other hand, is preferably implemented using a low-level programming language to allow finer control of the hardware, an essential trait in real-time processing applications. In this paper we present a technique that allows deploying DSP algorithms written in Julia, a modern high-level programming language, on a real-time HA processing platform known as openMHA. We demonstrate this technique by using a model-based Bayesian inference framework to perform real-time audio processing.

AB - Development of hearing aid (HA) signal processing algorithms entails an iterative process between two design steps, namely algorithm development and the embedded implementation. Algorithm designers favor high-level programming languages for several reasons including higher productivity, code readability and, perhaps most importantly, availability of state-of-the-art signal processing frameworks that open new research directions. Embedded software, on the other hand, is preferably implemented using a low-level programming language to allow finer control of the hardware, an essential trait in real-time processing applications. In this paper we present a technique that allows deploying DSP algorithms written in Julia, a modern high-level programming language, on a real-time HA processing platform known as openMHA. We demonstrate this technique by using a model-based Bayesian inference framework to perform real-time audio processing.

KW - audio signal processing

KW - Hearing impairment

KW - Julia

KW - openMHA

KW - real time

KW - digital audio signal processing

KW - hearing aids

UR - https://www.scopus.com/pages/publications/85086728795

U2 - 10.1145/3378678.3397528

DO - 10.1145/3378678.3397528

M3 - Conference contribution

SP - 82

EP - 85

BT - Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020

A2 - Stuijk, Sander

PB - Association for Computing Machinery, Inc.

ER -

Roa-Villescas M , de Vries A , Stuijk S , Corporaal H. Real-time audio processing for hearing aids using a model-based Bayesian inference framework. In Stuijk S, editor, Proceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020: SCOPES 2020. Association for Computing Machinery, Inc. 2020. p. 82-85 doi: 10.1145/3378678.3397528

Real-time audio processing for hearing aids using a model-based Bayesian inference framework

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this