Bird vocalization

Abstract: 1. Repertoire size and organization of songs appears to vary greatly across even closely related species of birds. Much of the apparent complexity of song organization can be described by the relatively simple principle of the Markov chain. 2. We examined long sequences of songs in five closely related North American thrushes using two methods of Markov analysis, one based on the maximum likelihood method of HOEL, the other based on information theory. Both methods employed computer simulation of zero, first, second, and higher order Markov chains for comparison with empirical data. 3. Results indicated that each of the five species employed Markov sequencing on more than one level of song organization. Thus six Swainson's thrushes show strict linear first order relationships both in song sequencing and syllables within songs. Two veerys show invariate order within songs, but more variable second order sequencing between songs. A hermit thrush maintained fixed order within songs, but showed first and second and perhaps even higher order song sequencing, and a larger song repertoire. In four wood thrushes, each individual used identical parts in the same section (B or C) of different song types, the usual order of sections being ABC. Sequencing of songs within this species appears to be based on a combination of second or higher order sequencing of individual parts in sections B and C, leading to great richness in repertoire. In three robins, we found syllables rather than songs the primary unit of organization, showing first and higher order sequencing. The resulting songs are extremely variable. 4. A continuum of increasingly complex Markov chaining in both song and syllables within song resembles one based on the genetic affinities of the birds. 5. The process of drift in forming larger repertoires, employing Markov principles as well, is discussed. 6. The usefulness of the Markov model as a common pervasive organizational principle in bird vocalization is stressed.

Abstract: This paper investigates acoustic modeling for recognition of bird species from audio field recordings. First, the acoustic scene is decomposed into isolated segments, corresponding to detected sinusoids. Each segment is represented by a sequence of the frequency and normalized magnitude values of the sinusoid. The temporal evolution of these features is modeled using hidden Markov models HMMs. A novel method for an unsupervised modeling of individual bird vocalization elements is proposed. The element models are initialized using HMM-based clustering and then further trained using an iterative maximum likelihood label re-assignment procedure. State duration modeling, performed in a post-recognition stage, is explored. Finally, we developed a hybrid deep neural network—hidden Markov model. The developed acoustic models are employed for bird species identification, detection of specific species, and recognition of multiple bird species vocalizing in a given recording. The detection system employs score normalization. Recognition of multiple bird species is performed based on maximizing the likelihood of a set of segments on a subset of bird species models, with penalization based on Bayesian information criterion applied. Experimental evaluations are performed on more than 37 h of sound field recordings, containing vocalizations of 48 bird species, plus more than 16 h of non-bird sound recordings. Using 3 s of the detected signal, the best system achieved: identification accuracy of 98.7%, detection with the equal error rate of 2.7%, and recognition accuracy of 97.3% and 95.4% when vocalizations of multiple bird species are present, with the number of bird species known and estimated, respectively.

Abstract: This paper deals with a project of Automatic Bird Species Recognition Based on Bird Vocalization. Eighteen bird species of 6 different families were analyzed. At first, human factor cepstral coefficients representing the given signal were calculated from particular recordings. In the next phase, using the voice activity detection system, segments of bird vocalizations were detected from which a likelihood rate, with which the given code value corresponds to the given model, was calculated using individual hidden Markov models. For each bird species, just one respective hidden Markov model was trained. The interspecific success of 81.2% has been reached. For classification into families, the success has reached 90.45%.

Abstract: This work focuses on reliable detection of bird sound emissions as recorded in the open field. Acoustic detection of avian sounds can be used for the automatized monitoring of multiple bird taxa and querying in long-term recordings for species of interest for researchers, conservation practitioners, and decision makers. Recordings in the wild can be very noisy due to the exposure of the microphones to a large number of audio sources originating from all distances and directions, the number and identity of which cannot be known a-priori. The co-existence of the target vocalizations with abiotic interferences in an unconstrained environment is inefficiently treated by current approaches of audio signal enhancement. A technique that would spot only bird vocalization while ignoring other audio sources is of prime importance. These difficulties are tackled in this work, presenting a deep autoencoder that maps the audio spectrogram of bird vocalizations to its corresponding binary mask that encircles the spectral blobs of vocalizations while suppressing other audio sources. The procedure requires minimum human attendance, it is very fast during execution, thus suitable to scan massive volumes of data, in order to analyze them, evaluate insights and hypotheses, identify patterns of bird activity that, hopefully, finally lead to design policies on biodiversity issues.