Ability evaluation of a voice activity detection algorithm in bioacoustics: A case study on poultry calls

Alireza Mahdavian, Saeid Minaei, Ce Yang, Farshad Almasganj, Shaban Rahimi, Peter M. Marchetto

Research output: Contribution to journalArticle

Abstract

Poultry is one of the most strategic source of human foods. There have been seen some hopeful signs of bioacoustics application to monitor the health condition of this vital food source. One of the obstacles is that the bird's call is combined with some unvoiced sounds and extracting the calls is not easy, especially when the bird is sick. This research is a report on successful application of some of the features involved in extracting healthy and non-healthy birds’ calls from their sound signals. One hundred and twenty birds from two genotypes – Ross and Cobb – were placed in two groups, a control and those challenged with respiratory diseases. They were reared and their sound was recorded daily. The vocal phrases of the recorded audio signals were extracted using the presented algorithm. Results of analysis showed that an increase in age and onset of illness are two factors that cause an error increase. Detection accuracy was calculated at 95% for healthy young birds and 72% for non-healthy birds. A significant part of this error is due to misclassing the calls as non-vocal segments. This meant that 97% of the activities classified as vocal phrases were, in fact, vocal. These results showed that the idea of such an easy-to-implement algorithm could potentially be employed for the coarselevel segmentation of some animal vocalization signals with reliable outputs, which is an essential and primary step in bioacoustics research.

Original languageEnglish (US)
Article number105100
JournalComputers and Electronics in Agriculture
Volume168
DOIs
StatePublished - Jan 2020

Fingerprint

Bioacoustics
bioacoustics
Poultry
Birds
poultry
case studies
bird
birds
Acoustic waves
Pulmonary diseases
respiratory disease
food
vocalization
respiratory tract diseases
segmentation
evaluation
detection
foods
Animals
genotype

Keywords

  • Audio features
  • Bioacoustics
  • Gallus gallus
  • Health monitoring
  • Respiratory diseases

Cite this

Ability evaluation of a voice activity detection algorithm in bioacoustics : A case study on poultry calls. / Mahdavian, Alireza; Minaei, Saeid; Yang, Ce; Almasganj, Farshad; Rahimi, Shaban; Marchetto, Peter M.

In: Computers and Electronics in Agriculture, Vol. 168, 105100, 01.2020.

Research output: Contribution to journalArticle

Mahdavian, Alireza ; Minaei, Saeid ; Yang, Ce ; Almasganj, Farshad ; Rahimi, Shaban ; Marchetto, Peter M. / Ability evaluation of a voice activity detection algorithm in bioacoustics : A case study on poultry calls. In: Computers and Electronics in Agriculture. 2020 ; Vol. 168.
@article{4ca5734269914e128d4d632a27ea4373,
title = "Ability evaluation of a voice activity detection algorithm in bioacoustics: A case study on poultry calls",
abstract = "Poultry is one of the most strategic source of human foods. There have been seen some hopeful signs of bioacoustics application to monitor the health condition of this vital food source. One of the obstacles is that the bird's call is combined with some unvoiced sounds and extracting the calls is not easy, especially when the bird is sick. This research is a report on successful application of some of the features involved in extracting healthy and non-healthy birds’ calls from their sound signals. One hundred and twenty birds from two genotypes – Ross and Cobb – were placed in two groups, a control and those challenged with respiratory diseases. They were reared and their sound was recorded daily. The vocal phrases of the recorded audio signals were extracted using the presented algorithm. Results of analysis showed that an increase in age and onset of illness are two factors that cause an error increase. Detection accuracy was calculated at 95{\%} for healthy young birds and 72{\%} for non-healthy birds. A significant part of this error is due to misclassing the calls as non-vocal segments. This meant that 97{\%} of the activities classified as vocal phrases were, in fact, vocal. These results showed that the idea of such an easy-to-implement algorithm could potentially be employed for the coarselevel segmentation of some animal vocalization signals with reliable outputs, which is an essential and primary step in bioacoustics research.",
keywords = "Audio features, Bioacoustics, Gallus gallus, Health monitoring, Respiratory diseases",
author = "Alireza Mahdavian and Saeid Minaei and Ce Yang and Farshad Almasganj and Shaban Rahimi and Marchetto, {Peter M.}",
year = "2020",
month = "1",
doi = "10.1016/j.compag.2019.105100",
language = "English (US)",
volume = "168",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

TY - JOUR

T1 - Ability evaluation of a voice activity detection algorithm in bioacoustics

T2 - A case study on poultry calls

AU - Mahdavian, Alireza

AU - Minaei, Saeid

AU - Yang, Ce

AU - Almasganj, Farshad

AU - Rahimi, Shaban

AU - Marchetto, Peter M.

PY - 2020/1

Y1 - 2020/1

N2 - Poultry is one of the most strategic source of human foods. There have been seen some hopeful signs of bioacoustics application to monitor the health condition of this vital food source. One of the obstacles is that the bird's call is combined with some unvoiced sounds and extracting the calls is not easy, especially when the bird is sick. This research is a report on successful application of some of the features involved in extracting healthy and non-healthy birds’ calls from their sound signals. One hundred and twenty birds from two genotypes – Ross and Cobb – were placed in two groups, a control and those challenged with respiratory diseases. They were reared and their sound was recorded daily. The vocal phrases of the recorded audio signals were extracted using the presented algorithm. Results of analysis showed that an increase in age and onset of illness are two factors that cause an error increase. Detection accuracy was calculated at 95% for healthy young birds and 72% for non-healthy birds. A significant part of this error is due to misclassing the calls as non-vocal segments. This meant that 97% of the activities classified as vocal phrases were, in fact, vocal. These results showed that the idea of such an easy-to-implement algorithm could potentially be employed for the coarselevel segmentation of some animal vocalization signals with reliable outputs, which is an essential and primary step in bioacoustics research.

AB - Poultry is one of the most strategic source of human foods. There have been seen some hopeful signs of bioacoustics application to monitor the health condition of this vital food source. One of the obstacles is that the bird's call is combined with some unvoiced sounds and extracting the calls is not easy, especially when the bird is sick. This research is a report on successful application of some of the features involved in extracting healthy and non-healthy birds’ calls from their sound signals. One hundred and twenty birds from two genotypes – Ross and Cobb – were placed in two groups, a control and those challenged with respiratory diseases. They were reared and their sound was recorded daily. The vocal phrases of the recorded audio signals were extracted using the presented algorithm. Results of analysis showed that an increase in age and onset of illness are two factors that cause an error increase. Detection accuracy was calculated at 95% for healthy young birds and 72% for non-healthy birds. A significant part of this error is due to misclassing the calls as non-vocal segments. This meant that 97% of the activities classified as vocal phrases were, in fact, vocal. These results showed that the idea of such an easy-to-implement algorithm could potentially be employed for the coarselevel segmentation of some animal vocalization signals with reliable outputs, which is an essential and primary step in bioacoustics research.

KW - Audio features

KW - Bioacoustics

KW - Gallus gallus

KW - Health monitoring

KW - Respiratory diseases

UR - http://www.scopus.com/inward/record.url?scp=85076587426&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076587426&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2019.105100

DO - 10.1016/j.compag.2019.105100

M3 - Article

AN - SCOPUS:85076587426

VL - 168

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

M1 - 105100

ER -