Automatic Detection and Recognition of Tonal Bird Sounds in Noisy Environments

Abstract

This paper presents a study of automatic detection and recognition of tonal bird sounds in noisy environments. The detection of spectro-temporal regions containing bird tonal vocalisations is based on exploiting the spectral shape to identify sinusoidal components in the short-time spectrum. The detection method provides tonal-based feature representation that is employed for automatic bird recognition. The recognition system uses Gaussian mixture models to model 165 different bird syllables, produced by 95 bird species. Standard models, as well as models compensating for the effect of the noise, are employed. Experiments are performed on bird sound recordings corrupted by White noise and real-world environmental noise. The proposed detection method shows high detection accuracy of bird tonal components. The employed tonal-based features show significant recognition accuracy improvements over the Mel-frequency cepstral coefficients, in both standard and noise-compensated models, and strong robustness to mismatch between the training and testing conditions.

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

“…Typically, the first stage of an automatic system is to parse the acoustic signal into isolated spectro-temporal segments. This is often performed using an energy-based thresholding that requires an estimate of noise level, e.g., [1], or by decomposition into sinusoidal components [1], [2], [3], [4]. A variety of approaches to feature representation of the spectro-temporal segments and their modelling were explored.…”

“…In a case of tonal bird vocalisations, the use of a sinusoidal detection for segmentation also offers a natural way of representing the segment as a temporal sequence of the frequencies of the detected sinusoid, which we refer to as frequency track. This representation was employed in a few earlier studies [1], [6] and also in our recent works [3], [4], [7], [8], [9], [10]. Among the acoustic modelling approaches, the most commonly used are Gaussian mixture models (GMM) [1], [3], hidden Markov models (HMMs) [1], [4], [6], [11], and decision trees [12].…”

“…This representation was employed in a few earlier studies [1], [6] and also in our recent works [3], [4], [7], [8], [9], [10]. Among the acoustic modelling approaches, the most commonly used are Gaussian mixture models (GMM) [1], [3], hidden Markov models (HMMs) [1], [4], [6], [11], and decision trees [12]. Several studies focused on detection of specific bird species [13], [14], [15].…”

Integration of Temporal Contextual Information for Robust Acoustic Recognition of Bird Species from Real-Field Data

“…In exception of most of the published work, in [17] waterfall noise was added to bird recordings and it was shown that the recognition of bird sounds in noisy conditions reduces significantly the recognition performance. In this article, we evaluate several different machine learning algorith ms on the task of bird species classificat ion in real-field conditions, under the concept of AMIBIO project (LIFE08-NAT-GR-000539: Automatic Acoustic Monitoring and Inventorying of Biodiversity, Project web-site: http://www.amibio-project.eu/).…”

“…Different parametric representations for the bird vocalizations audio signals have been used, among which Mel frequency cepstral coefficients [5,6,16,17] are the most widely used. Other audio features which have been proposed in the literature are the linear predictive coding [16], linear p redictive cepstral coefficients [16], spectral and temporal audio descriptors [12], and tonal-based features [17].…”