Bioacoustics-The International Journal of Animal Sound and Its Recording最新文献_第10页

High-level individuality in vocalizations of a well-known avian brood parasite: Asian koel (Eudynamys scolopacea L.) 一种著名的鸟类繁殖寄生虫：亚洲锦鸡（Eudynamys scolopacea L.）发声的高度个性

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-06-25 DOI: 10.1080/09524622.2020.1784281

A. A. Khan, I. Z. Qureshi

{"title":"High-level individuality in vocalizations of a well-known avian brood parasite: Asian koel (Eudynamys scolopacea L.)","authors":"A. A. Khan, I. Z. Qureshi","doi":"10.1080/09524622.2020.1784281","DOIUrl":"https://doi.org/10.1080/09524622.2020.1784281","url":null,"abstract":"ABSTRACT The Asian koel (Eudynamys scolopacea) is a well-known brood parasitic bird that visits Pakistan every summer from India. This species produces at least five loud call types that are presumed to be used in territorial and mating behaviour. We noticed vocal differences among individuals in the wild and hypothesised that Asian koels produce individually distinct vocalizations. To test this, we recorded type 1 cooee calls, coe calls, type 1 coegh calls, type 2 coegh call and wurroo calls from 46 adult birds in the wild, and measured 15 different acoustic parameters, both spectral and temporal, for each vocalization type. We also measured the Potential of Individual Coding (PIC). Parameters having PIC values ≥1.1 were further analysed through stepwise cross-validated discriminant function analysis (DFA). The DFA accurately categorised 86.5% of the type 1 cooee calls, 95.7% of coe calls, 91.5% of the type 1 coegh calls, 82.2% of type 2 coegh calls and 83.3% of wurroo calls to the individuals from which these calls were recorded. Thus, consistent with our hypothesis, our results indicate that Asian koels produce individually distinct calls.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"26 1","pages":"379 - 388"},"PeriodicalIF":1.8,"publicationDate":"2020-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2020.1784281","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41305500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Acoustic and morphological variation on two populations of Dryophytes arenicolor in central México 青海中部两居群沙灰树的声学和形态变异

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-05-13 DOI: 10.1080/09524622.2020.1760937

Cristian I. Hernández-Herrera, H. A. Pérez-Mendoza

{"title":"Acoustic and morphological variation on two populations of Dryophytes arenicolor in central México","authors":"Cristian I. Hernández-Herrera, H. A. Pérez-Mendoza","doi":"10.1080/09524622.2020.1760937","DOIUrl":"https://doi.org/10.1080/09524622.2020.1760937","url":null,"abstract":"ABSTRACT Contrasting conditions of different habitats lead to geographic variation among populations of the same species. In widespread species, trait divergence represents a response to spatial variation in local habitat conditions and biotic interactions. Morphology and call characteristics are crucial for anuran fitness because of their direct impacts on survival and reproduction. Our aim was to analyse and compare morphological and call characteristics of two populations of Dryophytes arenicolor in central Mexico where waterbody types and presence of other species (D. eximius) differed. We measured morphological characteristics, estimated the sex ratio, and characterised the advertisement calls for each population. We found that the sex ratio differed among populations: in one population, the sex ratio was male-biased. No morphological variation was detected between populations; however, females had longer limbs and higher mass. We found differences in call characteristics among populations and even among individuals of the same population. There was an effect of calling context (solitary or chorus) on call characteristics, we found that calls from conspecifics led to an increase in values of spectral characteristics and reduction of temporal ones, whereas calls from D. eximius resulted in a decrease in values of spectral characteristics and increase in temporal ones.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"251 ","pages":"366 - 377"},"PeriodicalIF":1.8,"publicationDate":"2020-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2020.1760937","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41314679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Distributed representation of discrete sequential vocalization in the Bengalese finch (Lonchura striata var. domestica) 孟加拉雀(Lonchura striata var. domestica)离散顺序发声的分布表征

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-05-03 DOI: 10.1080/09524622.2019.1607558

Takuya Koumura, K. Okanoya

{"title":"Distributed representation of discrete sequential vocalization in the Bengalese finch (Lonchura striata var. domestica)","authors":"Takuya Koumura, K. Okanoya","doi":"10.1080/09524622.2019.1607558","DOIUrl":"https://doi.org/10.1080/09524622.2019.1607558","url":null,"abstract":"ABSTRACT Bengalese finches learn and produce sequential vocalizations with a complex song syntax. Various models for the song syntax have been proposed, each of which focuses on several different characteristics of the syntax. However, methods to model these multiple characteristics in a single framework have not been well studied. Here, we propose a model that explains three prominent characteristics of the song syntax in Bengalese finches in a single unified framework. First, the generation of a vocal element depends on multiple preceding elements. Second, a song often contains repetitions of a single element type. Third, a song often begins with a special sequence called an introductory sequence. In this study, an effective way was sought to model these three characteristics in the framework of a conditional probability in symbol sequences. The model takes a distributed representation of a preceding sequence as an input, which is defined by a set of decaying values activated when the vocal elements are generated. The proposed model is shown to outperform conventional syntax models in predicting sequences in novel songs. The results suggest that the song syntax of the bird’s brain might also be represented by decaying activities of populations of neurons.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"356 - 373"},"PeriodicalIF":1.8,"publicationDate":"2020-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2019.1607558","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46261252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring 自动声学野生动物监测中模板检测数据假阳性的统计学习缓解

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-05-03 DOI: 10.1080/09524622.2019.1605309

Cathleen Balantic, T. Donovan

{"title":"Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring","authors":"Cathleen Balantic, T. Donovan","doi":"10.1080/09524622.2019.1605309","DOIUrl":"https://doi.org/10.1080/09524622.2019.1605309","url":null,"abstract":"ABSTRACT Audio sampling of the environment can provide long-term, landscape-scale presence-absence data to model populations of sound-producing wildlife. Automated detection systems allow researchers to avoid manually searching through large volumes of recordings, but often produce unacceptable false positive rates. We developed methods that allow researchers to improve template-based automated detection using a suite of statistical learning algorithms when false positive rates are problematic. To test our method, we acquired 668 hours of recordings in the Sonoran Desert, California USA between March 2016 and May 2017, and created spectrogram cross-correlation templates for three target avian species. We trained and tested five classification algorithms and four performance-weighted ensemble classifier methods on target signals and false alarms from March 2016, and then selected high-performing ensemble classifiers from the train/test phase to predict the class of new detections thereafter. For three target species, our ensemble classifiers were able to identify 98%, 81%, and 100% of false alarms compared with the baseline template detection system, and comparative positive predictive values improved from 6% to 69%, 87% to 95%, and 2% to 77%. We show that statistical learning approaches can be implemented to mitigate false detections acquired via template-based automated detection in automated acoustic wildlife monitoring.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"296 - 321"},"PeriodicalIF":1.8,"publicationDate":"2020-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2019.1605309","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41463725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Adult female-calf acoustic communication signals in migrating east Australian humpback whales 迁徙的东澳大利亚座头鲸的成年雌性幼鲸声学通信信号

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-04-20 DOI: 10.1080/09524622.2020.1742204

Katherine L. Indeck, E. Girola, M. Torterotot, M. Noad, R. Dunlop

{"title":"Adult female-calf acoustic communication signals in migrating east Australian humpback whales","authors":"Katherine L. Indeck, E. Girola, M. Torterotot, M. Noad, R. Dunlop","doi":"10.1080/09524622.2020.1742204","DOIUrl":"https://doi.org/10.1080/09524622.2020.1742204","url":null,"abstract":"ABSTRACT Humpback whale (Megaptera novaeangliae) calf survival during migration is dependent upon them maintaining contact with their mothers, and acoustics likely plays a significant role in this. Here, we analysed calls (n = 255) produced by migrating humpback whale adult female-calf pairs (n = 15) off the east coast of Australia. First, we identified nine common call types that were then quantitatively separated into two distinct clusters. One cluster contained calls that were considerably longer in duration, lower in frequency, and narrower in bandwidth than those in the second cluster. These are proposed to have been produced by the adult females and calves, respectively. We then compared acoustic features within presumed age class. Minimum, peak, and maximum frequencies were significantly different across both adult females and calves (Kruskal-Wallis, p < 0.05), suggesting that their calls encode socially relevant information regarding physical signaller attributes (i.e. age and body size). This study established a baseline adult female-calf call repertoire produced during the migration of east Australian humpback whales. Potential vocal masking from anthropogenic noise is of particular concern for communications between adult females and their calves, as it may put calves at risk of becoming separated from their mothers.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"30 1","pages":"341 - 365"},"PeriodicalIF":1.8,"publicationDate":"2020-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2020.1742204","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42666354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Acoustic signals and repertoire complexity in Swallow-tailed Manakins (Chiroxiphia caudata, Aves: Pipridae) 燕尾Manakins (Chiroxiphia caudata，鸟类:Pipridae)的声信号和曲目复杂性

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-03-03 DOI: 10.1080/09524622.2018.1563870

L. M. Schaedler, P. H. L. Ribeiro, A. Guaraldo, L. Manica

{"title":"Acoustic signals and repertoire complexity in Swallow-tailed Manakins (Chiroxiphia caudata, Aves: Pipridae)","authors":"L. M. Schaedler, P. H. L. Ribeiro, A. Guaraldo, L. Manica","doi":"10.1080/09524622.2018.1563870","DOIUrl":"https://doi.org/10.1080/09524622.2018.1563870","url":null,"abstract":"ABSTRACT Neotropical manakins (Pipridae) are well known for the male’s multimodal courtship displays including acoustic and visual signals. In these birds, acoustic signals are important for attracting females to display arenas, often located at hidden perches within the forest. Here, we describe the acoustic repertoire of Swallow-tailed Manakins (Chiroxiphia caudata), a bird species well known for displaying cooperatively, but for which the acoustic repertoire has not been well-documented. We recorded calls and behaviour of Swallow-tailed Manakins on three display courts in the Atlantic Forest, Brazil. We classified calls to test our repertoire designations using linear discriminant analysis and asked how different sounds mapped onto components of the cooperative display. Prior to the display, males coordinate sounds either in duets, as has been shown in congeners, or in choruses, which we report for the first time in Chiroxiphia. Males also produce three mechanical sounds, so far undescribed in this species, and 11 calls associated with seven behaviours. Particularly prominent was the wah call produced while displaying, which becomes increasingly fast toward the jump display’s end, possibly to stimulate females for copulation. Our study of the Swallow-tailed Manakin acoustic repertoire provides insights into specific signal categories females may assess as they attend male mating displays.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"182 - 196"},"PeriodicalIF":1.8,"publicationDate":"2020-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2018.1563870","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43442400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Vocalizations of Rhinella sebbeni Vaz-Silva, Maciel, Bastos, and Pombal, 2015 (Anura: Bufonidae) Rhinella sebbeni Vaz Silva、Maciel、Bastos和Pombal的声乐，2015（Anura：蟾蜍科）

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-03-03 DOI: 10.1080/09524622.2018.1564069

Alejandro Valencia-Zuleta, Vinícius Guerra, Maria Augusta Guimarães Carvalho, Nathane de Queiroz Costa, Daniele Carvalho Do Carmo Faria, R. Bastos, N. M. Maciel

{"title":"Vocalizations of Rhinella sebbeni Vaz-Silva, Maciel, Bastos, and Pombal, 2015 (Anura: Bufonidae)","authors":"Alejandro Valencia-Zuleta, Vinícius Guerra, Maria Augusta Guimarães Carvalho, Nathane de Queiroz Costa, Daniele Carvalho Do Carmo Faria, R. Bastos, N. M. Maciel","doi":"10.1080/09524622.2018.1564069","DOIUrl":"https://doi.org/10.1080/09524622.2018.1564069","url":null,"abstract":"ABSTRACT Acoustic signals are used in diverse social contexts by frogs and serve as relevant tools for studies on evolution, description and identification of species. Here, we described the advertisement, aggressive and release calls of Rhinella sebbeni, a poorly known toad from the Rhinella margaritifera species group. The description of the vocal repertoire of R. sebbeni was based on eight males from the municipality of Terezópolis de Goiás, State of Goiás, Brazil. Calling activity of R. sebbeni is crepuscular and calls consist of non-harmonic pulsed notes. The advertisement call classified as type II, had an average duration of 0.299 s and dominant frequency of 1,266 Hz. Aggressive call duration was 0.288 s and dominant frequency of 1,292 Hz. Finally, the release call duration was 0.021 s and dominant frequency 979 Hz. We found that advertisement call of R. sebbeni and its calling activity were similar to those of other species in the R. margaritifera group. We argued that release calls are useful for identification in this taxonomically complex group. We also emphasize the importance of acoustic and natural history data to help clarify the taxonomic status of species belonging to groups such as R. margaritifera.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"197 - 209"},"PeriodicalIF":1.8,"publicationDate":"2020-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2018.1564069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42612182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

The perceptual effects of manipulating nonlinear phenomena in synthetic nonverbal vocalizations 操纵合成非言语发声中非线性现象的感知效应

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-03-03 DOI: 10.1080/09524622.2019.1581839

Andrey Anikin

{"title":"The perceptual effects of manipulating nonlinear phenomena in synthetic nonverbal vocalizations","authors":"Andrey Anikin","doi":"10.1080/09524622.2019.1581839","DOIUrl":"https://doi.org/10.1080/09524622.2019.1581839","url":null,"abstract":"ABSTRACT The communicative role of nonlinear vocal phenomena remains poorly understood since they are difficult to manipulate or even measure with conventional tools. In this study parametric voice synthesis was employed to add pitch jumps, subharmonics/sidebands, and chaos to synthetic human nonverbal vocalizations. In Experiment 1 (86 participants, 144 sounds), chaos was associated with lower valence, and subharmonics with higher dominance. Arousal ratings were not noticeably affected by any nonlinear effects, except for a marginal effect of subharmonics. These findings were extended in Experiment 2 (83 participants, 212 sounds) using ratings on discrete emotions. Listeners associated pitch jumps, subharmonics, and especially chaos with aversive states such as fear and pain. The effects of manipulations in both experiments were particularly strong for ambiguous vocalizations, such as moans and gasps, and could not be explained by a non-specific measure of spectral noise (harmonics-to-noise ratio) – that is, they would be missed by a conventional acoustic analysis. In conclusion, listeners interpret nonlinear vocal phenomena quite flexibly, depending on their type and the kind of vocalization in which they occur. These results showcase the utility of parametric voice synthesis and highlight the need for a more fine-grained analysis of voice quality in acoustic research.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"226 - 247"},"PeriodicalIF":1.8,"publicationDate":"2020-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2019.1581839","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41821272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16

Savannah sparrows (Passerculus sandwichensis) nesting close to energy infrastructure alarm call at a lower frequency 萨凡纳麻雀(雀鸟)在靠近能源基础设施筑巢时发出较低频率的警报

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-03-03 DOI: 10.1080/09524622.2018.1563869

Bridget Antze, N. Koper

{"title":"Savannah sparrows (Passerculus sandwichensis) nesting close to energy infrastructure alarm call at a lower frequency","authors":"Bridget Antze, N. Koper","doi":"10.1080/09524622.2018.1563869","DOIUrl":"https://doi.org/10.1080/09524622.2018.1563869","url":null,"abstract":"ABSTRACT Many birds rely on alarm calls during nest defence to communicate about risk, but anthropogenic disturbance, including noisy industrial infrastructure, has the potential to disrupt alarm communication. Birds may overcome these effects by altering the structure of vocalizations to improve signal transmission. While previous work has demonstrated that birds can alter the structure of songs in the presence of noise, few have considered effects of noise-producing infrastructure on alarm call structure. Here, we tested whether Savannah sparrows (Passerculus sandwichensis) altered the structure of alarm calls in the presence of natural gas compressor stations or grid-powered or generator-powered screw pump oil wells, and in relation to overall ambient noise levels. Savannah sparrows called at a lower peak frequency and first quartile frequency close to gas compressor stations, but call structure did not differ with proximity to either type of oil well, or in response to ambient noise levels, suggesting that factors beyond noise amplitude, such as the physical footprint of the infrastructure, affected call structure close to compressor stations. Our results demonstrate that even unlearned, structurally simple avian vocalizations can vary in structure, and that the impacts of anthropogenic infrastructure on acoustic communication may be driven by factors beyond just noise.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"168 - 181"},"PeriodicalIF":1.8,"publicationDate":"2020-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2018.1563869","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42844413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An unsupervised Hidden Markov Model-based system for the detection and classification of blue whale vocalizations off Chile 基于无监督隐马尔可夫模型的智利海域蓝鲸发声检测和分类系统

IF 1.8 4区生物学

Bioacoustics-The International Journal of Animal Sound and Its Recording Pub Date : 2020-03-03 DOI: 10.1080/09524622.2018.1563758

Susannah J. Buchan, R. Mahú, J. Wuth, Naysa Balcazar-Cabrera, Laura Gutiérrez, S. Neira, N. B. Yoma

{"title":"An unsupervised Hidden Markov Model-based system for the detection and classification of blue whale vocalizations off Chile","authors":"Susannah J. Buchan, R. Mahú, J. Wuth, Naysa Balcazar-Cabrera, Laura Gutiérrez, S. Neira, N. B. Yoma","doi":"10.1080/09524622.2018.1563758","DOIUrl":"https://doi.org/10.1080/09524622.2018.1563758","url":null,"abstract":"ABSTRACT In this paper, we present an automatic method, without human supervision, for the detection and classification of blue whale vocalizations from passive acoustic monitoring (PAM) data using Hidden Markov Model technology implemented with a state-of-the-art machine learning platform, the Kaldi speech processing toolkit. 157.5 hours of PAM data were annotated for model training and testing, selected from a dataset collected from the Corcovado Gulf, Chilean Patagonia in 2016. The system obtained produced 85.3% accuracy for detection and classification of a range of different blue whale vocalizations. This system was then validated by comparing its unsupervised detection and classification results with the published results of southeast Pacific blue whale song phrase (‘SEP2’) via spectrogram cross-correlation, involving a dataset collected with a different hydrophone instrument. The proposed system led to a reduction in the root mean square error relative to published results as high as 80% when compared with comparable methods employed elsewhere. This is a significant step in advancing the monitoring of endangered whale populations in this region, which remains poorly covered in terms of PAM and general ocean observation. With further training, testing and validation, this system can be applied to other target signals and regions of the world ocean.","PeriodicalId":55385,"journal":{"name":"Bioacoustics-The International Journal of Animal Sound and Its Recording","volume":"29 1","pages":"140 - 167"},"PeriodicalIF":1.8,"publicationDate":"2020-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/09524622.2018.1563758","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43390737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8