Whistle contour extraction aims to derive animal whistles from time-frequency spectrograms as polylines. For toothed whales, whistle extraction results can serve as the basis for analyzing animal abundance, species identity, and social activities. During the last few decades, as long-term recording systems have become affordable, automated whistle extraction algorithms were proposed to process large volumes of recording data. Recently, a deep learning-based method demonstrated superior performance in extracting whistles under varying noise conditions. However, training such networks requires a large amount of labor-intensive annotation, which is not available for many species. To overcome this limitation, we present a framework of stage-wise generative adversarial networks (GANs), which compile new whistle data suitable for deep model training via three stages: generation of background noise in the spectrogram, generation of whistle contours, and generation of whistle signals. By separating the generation of different components in the samples, our framework composes visually promising whistle data and labels even when few expert annotated data are available. Regardless of the amount of human-annotated data, the proposed data augmentation framework leads to a consistent improvement in performance of the whistle extraction model, with a maximum increase of 1.69 in the whistle extraction mean F1-score. Our stage-wise GAN also surpasses one single GAN in improving whistle extraction models with augmented data.

We present a learning-based method for extracting whistles of toothed whales (Odontoceti) in hydrophone recordings. Our method represents audio signals as time-frequency spectrograms and decomposes each spectrogram into a set of time-frequency patches. A deep neural network learns archetypical patterns (e.g., crossings, frequency modulated sweeps) from the spectrogram patches and predicts time-frequency peaks that are associated with whistles. We also developed a comprehensive method to synthesize training samples from background environments and train the network with minimal human annotation effort. We applied the proposed learn-from-synthesis method to a subset of the public Detection, Classification, Localization, and Density Estimation (DCLDE) 2011 workshop data to extract whistle confidence maps, which we then processed with an existing contour extractor to produce whistle annotations. The F1-score of our best synthesis method was 0.158 greater than our baseline whistle extraction algorithm (~25% improvement) when applied to common dolphin (Delphinus spp.) and bottlenose dolphin (Tursiops truncatus) whistles.

Delphinids produce large numbers of short duration, broadband echolocation clicks which may be useful for species classification in passive acoustic monitoring efforts. A challenge in echolocation click classification is to overcome the many sources of variability to recognize underlying patterns across many detections. An automated unsupervised network-based classification method was developed to simulate the approach a human analyst uses when categorizing click types: Clusters of similar clicks were identified by incorporating multiple click characteristics (spectral shape and inter-click interval distributions) to distinguish within-type from between-type variation, and identify distinct, persistent click types. Once click types were established, an algorithm for classifying novel detections using existing clusters was tested. The automated classification method was applied to a dataset of 52 million clicks detected across five monitoring sites over two years in the Gulf of Mexico (GOM). Seven distinct click types were identified, one of which is known to be associated with an acoustically identifiable delphinid (Risso's dolphin) and six of which are not yet identified. All types occurred at multiple monitoring locations, but the relative occurrence of types varied, particularly between continental shelf and slope locations. Automatically-identified click types from autonomous seafloor recorders without verifiable species identification were compared with clicks detected on sea-surface towed hydrophone arrays in the presence of visually identified delphinid species. These comparisons suggest potential species identities for the animals producing some echolocation click types. The network-based classification method presented here is effective for rapid, unsupervised delphinid click classification across large datasets in which the click types may not be known a priori.

In recent decades, the cost of acoustic technologies has declined dramatically. Advances in networks, storage devices, and power management have made it practical to consider the remote location of sensors. Nonetheless, many challenges remain for the fabrication, deployment, and use of remote sensors. This paper provides an overview of the issues involved in developing remote acoustic sensors. We discuss physical design and the integration of components, data storage and communication issues, signal acquisition and classification, and the relationship of these issues to power usage requirements

It is well known that simple amplification cannot help many hearing-impaired listeners. As a consequence of this, numerous signal enhancement algorithms have been proposed for digital hearing aids. Many of these algorithms are only effective in certain environments. The ability to quickly and correctly detect elements of the auditory scene can permit the selection/parameterization of enhancement algorithms from a library of available routines. In this work, the authors examine the real time parameterization of a frequency-domain compression algorithm which preserves formant ratios and thus enhances speech understanding for some individuals with severe sensorineural hearing loss in the 2-3 kHz range. The optimal compression ratio is dependent upon qualities of the acoustical signal. We briefly review the frequency-compression technology and describe a Gaussian mixture model classifier which can dynamically set the frequency compression ratio according to broad acoustic categories which we call cohorts. We discuss the results of a prototype simulator which has been implemented on a general purpose computer.

Previous work by Merhav and Lee (1993) as well as others has emphasized that the conditions required to make the maximum a posteriori (MAP) decision rule an optimal decision rule for speech recognition do not hold and have proposed techniques based upon the adjustment of model parameters to improve speech recognition. In this article, we consider the problem of text-independent speaker recognition, and present a new model called the integral decode. The integral decode, like previous work in this area, attempts to compensate for the lack of conditions necessary to ensure optimality of the MAP decision rule in environments with corrupted observations and imperfect models. The integral decode is a smoothing operation in the feature space domain. A region of uncertainty is established about each noisy observation and an approximation of the integral is computed. The MAP decision rule is then applied to the smoothed likelihood estimates. In all tested conditions, the integral decode performs as well as or better than equivalent HMMs without integral decode.