Forrest Briggs

Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach

Although field-collected recordings typically contain multiple simultaneously vocalizing birds of different species, acoustic species classification in this setting has received little study so far. This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with MIML classifiers. The proposed representation uses a 2D time-frequency segmentation of the audio signal, which can separate bird sounds that overlap in time. Experiments using audio data containing 13 species collected with unattended omnidirectional microphones in the H. J. Andrews Experimental Forest demonstrate that the proposed methods achieve high accuracy (96.1% true positives/negatives). Automated detection of bird species occurrence using MIML has many potential applications, particularly in long-term monitoring of remote sites, species distribution modeling, and conservation planning.

Time-frequency segmentation of bird song in noisy acoustic environments

Recent work in machine learning considers the problem of identifying bird species from an audio recording. Most methods require segmentation to isolate each syllable of bird call in input audio. Energy-based time-domain segmentation has been successfully applied to low-noise, single-bird recordings. However, audio from automated field recorders contains too much noise for such methods, so a more robust segmentation method is required. We propose a supervised time-frequency audio segmentation method using a Random Forest classifier, to extract syllables of bird call from a noisy signal. When applied to a test data set of 625 field-collected audio segments, our method isolates 93.6% of the acoustic energy of bird song with a false positive rate of 8.6%, outperforming energy thresholding.

Audio Classification of Bird Species: A Statistical Manifold Approach

Our goal is to automatically identify which species of bird is present in an audio recording using supervised learning. Devising effective algorithms for bird species classification is a preliminary step toward extracting useful ecological data from recordings collected in the field. We propose a probabilistic model for audio features within a short interval of time, then derive its Bayes risk-minimizing classifier, and show that it is closely approximated by a nearest-neighbor classifier using Kullback-Leibler divergence to compare histograms of features. We note that feature histograms can be viewed as points on a statistical manifold, and KL divergence approximates geodesic distances defined by the Fisher information metric on such manifolds. Motivated by this fact, we propose the use of another approximation to the Fisher information metric, namely the Hellinger metric. The proposed classifiers achieve over 90% accuracy on a data set containing six species of bird, and outperform support vector machines.

The 9th annual MLSP competition: New methods for acoustic classification of multiple simultaneous bird species in a noisy environment

Birds have been widely used as biological indicators for ecological research. They respond quickly to environmental changes and can be used to infer about other organisms (e.g., insects they feed on). Traditional methods for collecting data about birds involves costly human effort. A promising alternative is acoustic monitoring. There are many advantages to recording audio of birds compared to human surveys, including increased temporal and spatial resolution and extent, applicability in remote sites, reduced observer bias, and potentially lower cost. However, it is an open problem for signal processing and machine learning to reliably identify bird sounds in real-world audio data collected in an acoustic monitoring scenario. Some of the major challenges include multiple simultaneously vocalizing birds, other sources of non-bird sound (e.g., buzzing insects), and background noise like wind, rain, and motor vehicles.

Instance Annotation for Multi-Instance Multi-Label Learning

Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels. For example, an image can be represented as a bag of segments and associated with a list of objects it contains. Prior work on MIML has focused on predicting label sets for previously unseen bags. We instead consider the problem of predicting instance labels while learning from data labeled only at the bag level. We propose a regularized rank-loss objective designed for instance annotation, which can be instantiated with different aggregation models connecting instance-level labels with bag-level label sets. The aggregation models that we consider can be factored as a linear function of a “support instance” for each class, which is a single feature vector representing a whole bag. Hence we name our proposed methods rank-loss Support Instance Machines (SIM). We propose two optimization methods for the rank-loss objective, which is nonconvex. One is a heuristic method that alternates between updating support instances, and solving a convex problem in which the support instances are treated as constant. The other is to apply the constrained concave-convex procedure (CCCP), which can also be interpreted as iteratively updating support instances and solving a convex problem. To solve the convex problem, we employ the Pegasos framework of primal subgradient descent, and prove that it finds an ε-suboptimal solution in runtime that is linear in the number of bags, instances, and 1/ε. Additionally, we suggest a method of extending the linear learning algorithm to nonlinear classification, without increasing the runtime asymptotically. Experiments on artificial and real-world datasets including images and audio show that the proposed methods achieve higher accuracy than other loss functions used in prior work, e.g., Hamming loss, and recent work in ambiguous label classification.

Context-aware MIML instance annotation: exploiting label correlations with classifier chains

In multi-instance multi-label (MIML) instance annotation, the goal is to learn an instance classifier while training on a MIML dataset, which consists of bags of instances paired with label sets; instance labels are not provided in the training data. The MIML formulation can be applied in many domains. For example, in an image domain, bags are images, instances are feature vectors representing segments in the images, and the label sets are lists of objects or categories present in each image. Although many MIML algorithms have been developed for predicting the label set of a new bag, only a few have been specifically designed to predict instance labels. We propose MIML-ECC (ensemble of classifier chains), which exploits bag-level context through label correlations to improve instance-level prediction accuracy. The proposed method is scalable in all dimensions of a problem (bags, instances, classes, and feature dimension) and has no parameters that require tuning (which is a problem for prior methods). In experiments on two image datasets, a bioacoustics dataset, and two artificial datasets, MIML-ECC achieves higher or comparable accuracy in comparison with several recent methods and baselines.

Novelty detection under multi-label multi-instance framework

Novelty detection plays an important role in machine learning and signal processing. This paper studies novelty detection in a new setting where the data object is represented as a bag of instances and associated with multiple class labels, referred to as multi-instance multi-label (MIML) learning. Contrary to the common assumption in MIML that each instance in a bag belongs to one of the known classes, in novelty detection, we focus on the scenario where bags may contain novel-class instances. The goal is to determine, for any given instance in a new bag, whether it belongs to a known class or a novel class. Detecting novelty in the MIML setting captures many real-world phenomena and has many potential applications. For example, in a collection of tagged images, the tag may only cover a subset of objects existing in the images. Discovering an object whose class has not been previously tagged can be useful for the purpose of soliciting a label for the new object class. To address this novel problem, we present a discriminative framework for detecting new class instances. Experiments demonstrate the effectiveness of our proposed method, and reveal that the presence of unlabeled novel instances in training bags is helpful to the detection of such instances in testing stage.

Efficient Evaluation of Coding Strategies for Transcutaneous Language Communication

Communication of natural language via the skin has seen renewed interest with the advent of mobile devices and wearable technology. Efficient evaluation of candidate haptic encoding algorithms remains a significant challenge. We present 4 algorithms along with our methods for evaluation, which are based on discriminability, learnability, and generalizability. Advantageously, mastery of an extensive vocabulary is not required. Haptic displays used 16 or 32 vibrotactile actuators arranged linearly or as a grid on the arm. In Study 1, a two-alternative, forced-choice protocol tested the ability of 10 participants to detect differences in word pairs encoded by 3 acoustic algorithms: Frequency Decomposition (FD), Dominant Spectral Peaks (DSP), and Autoencoder (AE). Detection specificity was not different among the algorithms, but sensitivity was significantly worse with AE than with FD or DSP. Study 2 compared the performance of 16 participants randomized to DSP vs a phoneme-based algorithm (PH) using a custom video game for training and testing. The PH group performed significantly better at all test stages, and showed better recognition and retention of words along with evidence of generalizability to new words.

Context-Aware MIML Instance Annotation

In multi-instance multi-label (MIML) instance annotation, the goal is to learn an instance classifier while training on a MIML dataset, which consists of bags of instances paired with label sets, instance labels are not provided in the training data. The MIML formulation can be applied in many domains. For example, in an image domain, bags are images, instances are feature vectors representing segments in the images, and the label sets are lists of objects or categories present in each image. Although many MIML algorithms have been developed for predicting the label set of a new bag, only a few have been specifically designed to predict instance labels. We propose MIML-ECC (ensemble of classifier chains), which exploits bag-level context through label correlations to improve instance-level prediction accuracy. The proposed method is scalable in all dimensions of a problem (bags, instances, classes, and feature dimension), and has no parameters that require tuning (which is a problem for prior methods). In experiments on two image datasets, a bioacoustics dataset, and two artificial datasets, MIML-ECC achieves higher or comparable accuracy in comparison to several recent methods and baselines.

Regularized joint density estimation for multi-instance learning

We present regularized multiple density estimation (MDE) using the maximum entropy (MaxEnt) framework for multi-instance datasets. In this approach, bags of instances are represented as distributions using the principle of MaxEnt. We learn basis functions which span the space of distributions for jointly regularized density estimation. The basis functions are analogous to topics in a topic model. We propose a distance metric for measuring similarities at the bag level which captures the statistical properties of each bag. We provide a convex optimization method to learn the metric and compare the results with distance based multi-instance learning algorithms, e.g., Citation-kNN and bag-level kernel SVM on two real world datasets. The results show that regularized MDE produces a comparable results in terms of accuracy with reduced computational complexity.