Learning to localize sounds in a highly reverberant environment: Machine-learning tracking of dolphin whistle-like sounds in a pool

Woodward, Sean; Reiss, Diana; Magnasco, Marcelo O.

doi:10.1371/journal.pone.0235155

Cited by 4 publications

(4 citation statements)

References 77 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, passive acoustic monitoring with towed or moored hydrophones (Mellinger et al, 2007) would be especially useful for detecting deep-diving and cryptic species (K. sima, Ziphiids), as well as Odontocetes or Balaenopterids with distinctive acoustic signatures, such as clicking sperm whales and singing humpback and blue whales. Relative to visual methods, acoustic data may not always provide accurate species identification or group size estimates, but recent advances on automated detection of broad-band echolocation clicks and tonal sounds (e.g., Gillispie et al, 2009;Frasier et al, 2017), as well as machine learning tools (e.g., Beslin et al, 2018;Bermant et al, 2019;Woodward et al, 2020) offer promising solutions.…”

Section: Methodological Approachesmentioning

confidence: 99%

Priorities for ecological research on cetaceans in the Galápagos Islands

Palacios

Cantor²

2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Located in the eastern tropical Pacific, the Galápagos Islands are an oceanic insular ecosystem subject to strong environmental variability driven by local and regional processes. Past research has shown that such conditions can attract and sustain at least 23 cetacean species, out of which 14 are common, including nine Delphinids, one Ziphiid, one Physeterid, and three Balaenopterids. These species occupy both coastal and oceanic habitats, most are present year-round, and a few are migratory. However, research on cetaceans in Galápagos has been sporadic and chronically underfunded and is not currently considered a priority in the research agenda for Galápagos. Based on a review of existing information and an assessment of knowledge gaps, here we identify priorities for ecological research on cetaceans in Galápagos along five topical areas: 1) spatiotemporal occurrence, 2) population assessment, 3) health assessment, 4) social ecology, and 5) trophic ecology. Addressing these knowledge gaps will also help inform actions to preserve cetacean biodiversity and to manage human activities involving or affecting cetaceans in Galápagos. Given the logistical and funding challenges of conducting cetacean research in Galápagos, we recommend optimizing data sampling and accessibility via integrated research protocols and open data repositories. We also recommend capitalizing on local citizen science activities, such as those conducted from cruise ships and whale-watching tours, which can serve as platforms of opportunity for obtaining basic data, thereby contributing to long-term data acquisition. Our proposed priorities should be assessed by Ecuadorian and Galápagos governmental institutions in broad and inclusive consultation with stakeholders and the scientific community prior to development and implementation of a research agenda. Collectively, these efforts will advance our understanding of the ecological role that marine megafauna, such as cetaceans, play in Galápagos and other oceanic islands, including maintaining large-scale connectivity and mitigating climate change.

show abstract

Section: Methodological Approachesmentioning

confidence: 99%

Priorities for ecological research on cetaceans in the Galápagos Islands

Palacios

Cantor²

2023

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…While less sensitive to details, they may be more resilient to noise in recordings in the wild ( Kohlsdorf et al, 2016 ; Jansen et al, 2020 ; Allen et al, 2021 ). Similar machine learning approaches have also recently been applied to the bioacoustically relevant case of localizing where a sound came from in a complex acoustical environment ( Woodward et al, 2020 ). Such advanced methods are relevant for the environments that foster dolphin whistled communications and human whistled languages because they are necessary in environments where sound is obstructed by obstacles or where there are massive reflections (reverberation).…”

Section: Technical Approaches For a Comparative Analysis Of Biological Whistlesmentioning

confidence: 99%

The Relevance of Human Whistled Languages for the Analysis and Decoding of Dolphin Communication

2021

Self Cite

View full text Add to dashboard Cite

Humans use whistled communications, the most elaborate of which are commonly called “whistled languages” or “whistled speech” because they consist of a natural type of speech. The principle of whistled speech is straightforward: people articulate words while whistling and thereby transform spoken utterances by simplifying them, syllable by syllable, into whistled melodies. One of the most striking aspects of this whistled transformation of words is that it remains intelligible to trained speakers, despite a reduced acoustic channel to convey meaning. It constitutes a natural traditional means of telecommunication that permits spoken communication at long distances in a large diversity of languages of the world. Historically, birdsong has been used as a model for vocal learning and language. But conversely, human whistled languages can serve as a model for elucidating how information may be encoded in dolphin whistle communication. In this paper, we elucidate the reasons why human whistled speech and dolphin whistles are interesting to compare. Both are characterized by similar acoustic parameters and serve a common purpose of long distance communication in natural surroundings in two large brained social species. Moreover, their differences – e.g., how they are produced, the dynamics of the whistles, and the types of information they convey – are not barriers to such a comparison. On the contrary, by exploring the structure and attributes found across human whistle languages, we highlight that they can provide an important model as to how complex information is and can be encoded in what appears at first sight to be simple whistled modulated signals. Observing details, such as processes of segmentation and coarticulation, in whistled speech can serve to advance and inform the development of new approaches for the analysis of whistle repertoires of dolphins, and eventually other species. Human whistled languages and dolphin whistles could serve as complementary test benches for the development of new methodologies and algorithms for decoding whistled communication signals by providing new perspectives on how information may be encoded structurally and organizationally.

show abstract

“…These methods estimate the direction of arrival of the wave from a source by means of signal component analysis or noise reduction. There is also a series of supporting techniques for reducing the influence of reverberation; efforts to that end include (i) reducing the background noise based on eigenvalue identification [10], (ii) single-source points enhancement [11,12], (iii) using early response to extract direct signals [13,14], and (iv) sampled data processing via weighted clusters [15] and machine learning [16][17][18][19], to name a few. In particular, sparse recovery has been used in recent years as a basic framework for solving ill-posed problems and very widely in various types of localization methods.…”

Section: Introductionmentioning

confidence: 99%

Indoor Sound Source Localization via Inverse Element-Free Simulation Based on Joint Sparse Recovery

Wang,

He,

Peng

et al. 2023

Electronics

View full text Add to dashboard Cite

Indoor sound source localization is a key technique in many engineering applications, and an inverse element-free method based on joint sparse recovery in a Bayesian framework is proposed for reverberant environments. In this method, a discrete wave model is constructed to represent the relationships between the sampled sound pressure and the source intensity distribution, and localization in the reverberant environment is realized via inversion from the wave model. By constructing a compact supporting domain, the source intensity can be sparsely represented in subdomains, and the sparse Bayesian framework is used to recover the source intensity. In particular, joint sparse recovery in the frequency domain is exploited to improve the recovery performance. Numerical and experimental verifications show that, compared with another state-of-the-art method, the proposed method achieves high source-localization accuracy and low sidelobes with low computational complexity in highly reverberant environments.

show abstract

Learning to localize sounds in a highly reverberant environment: Machine-learning tracking of dolphin whistle-like sounds in a pool

Cited by 4 publications

References 77 publications

Priorities for ecological research on cetaceans in the Galápagos Islands

Priorities for ecological research on cetaceans in the Galápagos Islands

The Relevance of Human Whistled Languages for the Analysis and Decoding of Dolphin Communication

Indoor Sound Source Localization via Inverse Element-Free Simulation Based on Joint Sparse Recovery

Contact Info

Product

Resources

About