Automatic detection of bird species from audio field recordings using HMM-based modelling of frequency tracks

This paper presents an automatic system for detection of bird species in field recordings. A sinusoidal detection algorithm is employed to segment the acoustic scene into isolated spectro-temporal segments. Each segment is represented as a temporal sequence of frequencies of the detected sinusoid, referred to as frequency track. Each bird species is represented by a set of hidden Markov models (HMMs), each HMM modelling an individual type of bird vocalisation element. These HMMs are obtained in an unsupervised manner. The detection is based on a likelihood ratio of the test utterance against the target bird species and non-target background model. We explore on selection of cohort for modelling the background model, z-norm and t-norm score normalisation techniques and score compensation to deal with outlier data. Experiments are performed using over 40 hours of audio field recordings from 48 bird species plus an additional 16 hours of field recordings as impostor trials. Evaluations are performed using detection error trade-off plots. The equal error rate of 5% is achieved when impostor trials are non-target bird species vocalisations and 1.2% when using field recordings which do not contain bird vocalisations.

• Publication year

  2017

• Venue

  European Signal Processing Conference

• Publication date

  2017-08-01

• Fields of study

  Biology, Computer Science, Environmental Science

• Identifiers
  DOI 10.23919/EUSIPCO.2017.8081515
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Automated Sound Recognition Provides Insights into the Behavioral Ecology of a Tropical Bird

  2017cited by this paper
• Bird species recognition using HMM-based unsupervised modelling of individual syllables with incorporated duration modelling

  2016cited by this paper
• Improved Automatic Bird Identification through Decision Tree based Feature Selection and Bagging

  2015cited by this paper
• HMM-based modelling of individual syllables for bird species recognition from audio field recordings

  2015cited by this paper
• Acoustic Recognition of Multiple Bird Species Based on Penalized Maximum Likelihood

  2015cited by this paper
• Bird species recognition from field recordings using HMM-based modelling of frequency tracks

  2014cited by this paper
• A practical comparison of manual and autonomous methods for acoustic monitoring

  2013cited by this paper
• Unsupervised discovery of acoustic patterns in bird vocalisations employing DTW and clustering

  2013cited by this paper
• An Open Dataset for Research on Audio Field Recording Archives: freefield1010

  2013cited by this paper
• Acoustic classification of multiple simultaneous bird species: a multi-instance multi-label approach.

  2012cited by this paper
• Automatic Detection and Recognition of Tonal Bird Sounds in Noisy Environments

  2011cited by this paper
• Detection of sinusoidal signals in noise by probabilistic modelling of the spectral magnitude shape and phase continuity

  2011cited by this paper
• Noise robust bird song detection using syllable pattern-based hidden Markov models

  2011cited by this paper
• Detecting bird sounds in a complex acoustic environment and application to bioacoustic monitoring

  2010cited by this paper
• Automatic recognition of harmonic bird sounds using a frequency track extraction algorithm.

  2008cited by this paper
• Feature Vector Selection and Use With Hidden Markov Models to Identify Frequency-Modulated Bioacoustic Signals Amidst Noise

  2008cited by this paper
• Parametric Representations of Bird Sounds for Automatic Species Recognition

  2006influential reference
• Reliability-based estimation of the number of noisy features: application to model-order selection in the union models

  2003cited by this paper
• Speaker verification over the telephone

  2000cited by this paper
• Score Normalization for Text-Independent Speaker Verification Systems

  2000cited by this paper
• The DET curve in assessment of detection task performance

  1997cited by this paper
• Speaker identification and verification using Gaussian mixture speaker models

  1995cited by this paper

• Automated Bird Species Identification using Audio Signal Processing and Convolutional Neural Network

  2024cites this paper
• Low Resource Species Agnostic Bird Activity Detection

  2021cites this paper
• Multi-Background Island Bird Detection Based on Faster R-CNN

  2020cites this paper
• Automated Bird Species Identification For Conservation

  year unknowncites this paper