Voice Quality Improvement with Error Concealment in Audio Sensor Networks

Okan Türkes; Sebnem Baydere

doi:10.1007/978-3-642-30630-3_27

Voice Quality Improvement with Error Concealment in Audio Sensor Networks

Okan Türkes, Sebnem Baydere

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

3 Citations (Scopus)

13 Downloads (Pure)

Abstract

Multi-dimensional properties of audio data and resource-poor nodes make voice processing and transmission a challenging task for Wireless Sensor Networks (WSN). This study analyzes voice quality distortions caused by packet losses occurring over a multi-hop WSN testbed: A comprehensive analysis of transmitted voice quality is given in a real setup. In the experiments, recorded signals are partitioned into data segments and delivered efficiently at the source. Throughout the network, two reconstruction scenarios are considered for the lost segments: In the first one, a raw projection is applied on voice with no error concealment (V-NC) whereas the latter encodes a simple error concealment (V-EC). It is shown that with an affordable reconstruction, a comprehensible voice can be gathered even when packet error rate is as high as 30%.

Original language	Undefined
Title of host publication	Proceedings of the 10th International Conference on Wired / Wireless Internet Communication, WWIC 2012
Place of Publication	Berlin
Publisher	Springer
Pages	307-314
Number of pages	8
ISBN (Print)	978-3-642-30629-7
DOIs	https://doi.org/10.1007/978-3-642-30630-3_27
Publication status	Published - 6 Jun 2012
Event	10th International Conference on Wired/Wireless Internet Communications, WWIC 2012 - Santorini, Greece Duration: 6 Jun 2012 → 8 Jun 2012 Conference number: 10

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	7277
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	10th International Conference on Wired/Wireless Internet Communications, WWIC 2012
Abbreviated title	WWIC
Country	Greece
City	Santorini
Period	6/06/12 → 8/06/12

Keywords

METIS-287908
IR-80773
Audio sensor networks
error concealment
voice coding
voice quality assessment
EWI-22013
wireless multimedia sensor networks

Access to Document

10.1007/978-3-642-30630-3_27

fulltext-20
open

Cite this

Türkes, O., & Baydere, S. (2012). Voice Quality Improvement with Error Concealment in Audio Sensor Networks. In Proceedings of the 10th International Conference on Wired / Wireless Internet Communication, WWIC 2012 (pp. 307-314). (Lecture Notes in Computer Science; Vol. 7277). Berlin: Springer. https://doi.org/10.1007/978-3-642-30630-3_27

@inproceedings{8d5b69b746f44f2984e6e1e711c2c60c,

title = "Voice Quality Improvement with Error Concealment in Audio Sensor Networks",

abstract = "Multi-dimensional properties of audio data and resource-poor nodes make voice processing and transmission a challenging task for Wireless Sensor Networks (WSN). This study analyzes voice quality distortions caused by packet losses occurring over a multi-hop WSN testbed: A comprehensive analysis of transmitted voice quality is given in a real setup. In the experiments, recorded signals are partitioned into data segments and delivered efficiently at the source. Throughout the network, two reconstruction scenarios are considered for the lost segments: In the first one, a raw projection is applied on voice with no error concealment (V-NC) whereas the latter encodes a simple error concealment (V-EC). It is shown that with an affordable reconstruction, a comprehensible voice can be gathered even when packet error rate is as high as 30{\%}.",

keywords = "METIS-287908, IR-80773, Audio sensor networks, error concealment, voice coding, voice quality assessment, EWI-22013, wireless multimedia sensor networks",

author = "Okan T{\"u}rkes and Sebnem Baydere",

note = "10.1007/978-3-642-30630-3_27",

year = "2012",

month = "6",

day = "6",

doi = "10.1007/978-3-642-30630-3_27",

language = "Undefined",

isbn = "978-3-642-30629-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "307--314",

booktitle = "Proceedings of the 10th International Conference on Wired / Wireless Internet Communication, WWIC 2012",

}

Türkes, O & Baydere, S 2012, Voice Quality Improvement with Error Concealment in Audio Sensor Networks. in Proceedings of the 10th International Conference on Wired / Wireless Internet Communication, WWIC 2012. Lecture Notes in Computer Science, vol. 7277, Springer, Berlin, pp. 307-314, 10th International Conference on Wired/Wireless Internet Communications, WWIC 2012, Santorini, Greece, 6/06/12. https://doi.org/10.1007/978-3-642-30630-3_27

Voice Quality Improvement with Error Concealment in Audio Sensor Networks. / Türkes, Okan; Baydere, Sebnem.

Proceedings of the 10th International Conference on Wired / Wireless Internet Communication, WWIC 2012. Berlin : Springer, 2012. p. 307-314 (Lecture Notes in Computer Science; Vol. 7277).

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

TY - GEN

T1 - Voice Quality Improvement with Error Concealment in Audio Sensor Networks

AU - Türkes, Okan

AU - Baydere, Sebnem

N1 - 10.1007/978-3-642-30630-3_27

PY - 2012/6/6

Y1 - 2012/6/6

N2 - Multi-dimensional properties of audio data and resource-poor nodes make voice processing and transmission a challenging task for Wireless Sensor Networks (WSN). This study analyzes voice quality distortions caused by packet losses occurring over a multi-hop WSN testbed: A comprehensive analysis of transmitted voice quality is given in a real setup. In the experiments, recorded signals are partitioned into data segments and delivered efficiently at the source. Throughout the network, two reconstruction scenarios are considered for the lost segments: In the first one, a raw projection is applied on voice with no error concealment (V-NC) whereas the latter encodes a simple error concealment (V-EC). It is shown that with an affordable reconstruction, a comprehensible voice can be gathered even when packet error rate is as high as 30%.

AB - Multi-dimensional properties of audio data and resource-poor nodes make voice processing and transmission a challenging task for Wireless Sensor Networks (WSN). This study analyzes voice quality distortions caused by packet losses occurring over a multi-hop WSN testbed: A comprehensive analysis of transmitted voice quality is given in a real setup. In the experiments, recorded signals are partitioned into data segments and delivered efficiently at the source. Throughout the network, two reconstruction scenarios are considered for the lost segments: In the first one, a raw projection is applied on voice with no error concealment (V-NC) whereas the latter encodes a simple error concealment (V-EC). It is shown that with an affordable reconstruction, a comprehensible voice can be gathered even when packet error rate is as high as 30%.

KW - METIS-287908

KW - IR-80773

KW - Audio sensor networks

KW - error concealment

KW - voice coding

KW - voice quality assessment

KW - EWI-22013

KW - wireless multimedia sensor networks

U2 - 10.1007/978-3-642-30630-3_27

DO - 10.1007/978-3-642-30630-3_27

M3 - Conference contribution

SN - 978-3-642-30629-7

T3 - Lecture Notes in Computer Science

SP - 307

EP - 314

BT - Proceedings of the 10th International Conference on Wired / Wireless Internet Communication, WWIC 2012

PB - Springer

CY - Berlin

ER -