Marie A. Roch

Marie A. Roch

Auto-generated profile, based on publicly available information

Marie A. Roch

Department of Computer Science, San Diego State University, San Diego, USA

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2011 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
PDF file
MRMarie A. Roch
Marie A. Roch
HKHolger Klinck
Holger Klinck
SBSimone Baumann-Pickering
Simone Baumann-Pickering
DMDavid K. Mellinger
David K. Mellinger
SQSimon Qui
Simon Qui
JHJohn A. Hildebrand
John A. Hildebrand
This study presents a system for classifying echolocation clicks of six species of odontocetes in the Southern California Bight: Visually confirmed bottlenose dolphins, short- and long-beaked common dolphins, Pacific white-sided dolphins, Risso’s dolphins, and presumed Cuvier’s beaked whales. Echolocation clicks are represented by cepstral feature vectors that are classified by Gaussian mixture models. A randomized cross-validation experiment is designed to provide conditions similar to those found in a field-deployed system. To prevent matched conditions from inappropriately lowering the error rate, echolocation clicks associated with a single sighting are never split across the training and test data. Sightings are randomly permuted before assignment to folds in the experiment. This allows different combinations of the training and test data to be used while keeping data from each sighting entirely in the training or test set. The system achieves a mean error rate of 22% across 100 randomized three-fold cross-validation experiments. Four of the six species had mean error rates lower than the overall mean, with the presumed Cuvier’s beaked whale clicks showing the best performance (<2% error rate). Long-beaked common and bottlenose dolphins proved the most difficult to classify, with mean error rates of 53% and 68%, respectively.

1 October 2011 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
MRMarie A. Roch
Marie A. Roch
TBT. Scott Brandes
T. Scott Brandes
BPBhavesh Patel
Bhavesh Patel
YBYvonne Barkley
Yvonne Barkley
SBSimone Baumann-Pickering
Simone Baumann-Pickering
MSMelissa S. Soldevilla
Melissa S. Soldevilla
Many odontocetes produce frequency modulated tonal calls known as whistles. The ability to automatically determine time × frequency tracks corresponding to these vocalizations has numerous applications including species description, identification, and density estimation. This work develops and compares two algorithms on a common corpus of nearly one hour of data collected in the Southern California Bight and at Palmyra Atoll. The corpus contains over 3000 whistles from bottlenose dolphins, long- and short-beaked common dolphins, spinner dolphins, and melon-headed whales that have been annotated by a human, and released to the Moby Sound archive. Both algorithms use a common signal processing front end to determine time × frequency peaks from a spectrogram. In the first method, a particle filter performs Bayesian filtering, estimating the contour from the noisy spectral peaks. The second method uses an adaptive polynomial prediction to connect peaks into a graph, merging graphs when they cross. Whistle contours are extracted from graphs using information from both sides of crossings. The particle filter was able to retrieve 71.5% (recall) of the human annotated tonals with 60.8% of the detections being valid (precision). The graph algorithm’s recall rate was 80.0% with a precision of 76.9%.

1 March 2007 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
PDF file
MRMarie A. Roch
Marie A. Roch
MSMelissa S. Soldevilla
Melissa S. Soldevilla
JBJessica C. Burtenshaw
Jessica C. Burtenshaw
EHE. Elizabeth Henderson
E. Elizabeth Henderson
JHJohn A. Hildebrand
John A. Hildebrand
A method for the automatic classification of free-ranging delphinid vocalizations is presented. The vocalizations of short-beaked and long-beaked common (Delphinus delphis and Delphinus capensis), Pacific white-sided (Lagenorhynchus obliquidens), and bottlenose (Tursiops truncatus) dolphins were recorded in a pelagic environment of the Southern California Bight and the Gulf of California over a period of 4 years. Cepstral feature vectors are extracted from call data which contain simultaneous overlapping whistles, burst-pulses, and clicks from a single species. These features are grouped into multisecond segments. A portion of the data is used to train Gaussian mixture models of varying orders for each species. The remaining call data are used to test the performance of the models. Species are predicted based upon probabilistic measures of model similarity with test segment groups having durations between 1 and 25s . For this data set, 256 mixture Gaussian mixture models and segments of at least 10s of call data resulted in the best classification results. The classifier predicts the species of groups with 67%–75% accuracy depending upon the partitioning of the training and test data.

21 July 2021 in Journal of The Royal Society Interface
Verified
Journal Article
Open access
SMShyam Madhusudhana
Shyam Madhusudhana
YSYu Shiu
Yu Shiu
HKHolger Klinck
Holger Klinck
EFErica Fleishman
Erica Fleishman
XLXiaobai Liu
Xiaobai Liu
MRMarie A. Roch
Marie A. Roch
Many animals rely on long-form communication, in the form of songs, for vital functions such as mate attraction and territorial defence. We explored the prospect of improving automatic recognition performance by using the temporal context inherent in song. The ability to accurately detect sequences of calls has implications for conservation and biological studies. We show that the performance of a convolutional neural network (CNN), designed to detect song notes (calls) in short-duration audio segments, can be improved by combining it with a recurrent network designed to process sequences of learned representations from the CNN on a longer time scale. The combined system of independently trained CNN and long short-term memory (LSTM) network models exploits the temporal patterns between song notes. We demonstrate the technique using recordings of fin whale ( Balaenoptera physalus ) songs, which comprise patterned sequences of characteristic notes. We evaluated several variants of the CNN + LSTM network. Relative to the baseline CNN model, the CNN + LSTM models reduced performance variance, offering a 9–17% increase in area under the precision–recall curve and a 9–18% increase in peak F1-scores. These results show that the inclusion of temporal information may offer a valuable pathway for improving the automatic recognition and transcription of wildlife recordings.

27 August 2022 in Methods in Ecology and Evolution
Verified
Journal Article
Open access
VDVlad Demartsev
Vlad Demartsev
AGAndrew S. Gersick
Andrew S. Gersick
FJFrants H. Jensen
Frants H. Jensen
MTMara Thomas
Mara Thomas
MRMarie A. Roch
Marie A. Roch
ASAriana Strandburg‐Peshkin
Ariana Strandburg‐Peshkin
Investigations of collective movement and animal communication have often followed distinct, though complementary, trajectories. Both subfields are deeply concerned with how information flows between individuals and shapes subsequent behaviour. Collective movement has largely focused on the dynamics of passive, cue‐mediated group coordination, while animal communication has primarily examined the content and function of active dyadic signal exchanges in sender–receiver frameworks. However, in many social groups, network‐wide signalling and collective movement decisions are tightly linked. Here we discuss opportunities afforded by using multi‐sensor tracking tags to simultaneously monitor the fine‐scale movements and vocalisations of entire social groups. We highlight how such data can elucidate the role of vocal signals in individual and collective movement while illuminating the structures of entire vocal‐interaction sequences at previously unexamined timescales and across entire communication networks. We identify practical and analytical challenges associated with these new tools and datasets, and present avenues for addressing them. We specifically address issues associated with the deployment and synchronisation of multiple tags, the processing and interpretation of resulting multidimensional datasets, and the benefits of combining tag‐based data collection with experimental approaches. Finally, we argue that a comparative approach employing consistent methodologies across a range of environments, populations and systems is needed to shed light on the evolutionary ecology of communication and collective behaviour.

9 June 2022 in Journal of Animal Ecology
Verified
Journal Article
Open access
MTMara Thomas
Mara Thomas
FJFrants H. Jensen
Frants H. Jensen
BABaptiste Averly
Baptiste Averly
VDVlad Demartsev
Vlad Demartsev
MMMarta B. Manser
Marta B. Manser
ASAriana Strandburg‐Peshkin
Ariana Strandburg‐Peshkin
Background: The manual detection, analysis and classification of animal vocalizations in acoustic recordings is laborious and requires expert knowledge. Hence, there is a need for objective, generalizable methods that detect underlying patterns in these data, categorize sounds into distinct groups and quantify similarities between them. Among all computational methods that have been proposed to accomplish this, neighbourhood‐based dimensionality reduction of spectrograms to produce a latent space representation of calls stands out for its conceptual simplicity and effectiveness. Goal of the study/what was done: Using a dataset of manually annotated meerkatSuricata suricattavocalizations, we demonstrate how this method can be used to obtain meaningful latent space representations that reflect the established taxonomy of call types. We analyse strengths and weaknesses of the proposed approach, give recommendations for its usage and show application examples, such as the classification of ambiguous calls and the detection of mislabelled calls. What this means: All analyses are accompanied by example code to help researchers realize the potential of this method for the study of animal vocalizations.