Université Grenoble Alpes (UGA)
11 rue des Mathématiques
38402 Saint Martin d’Hères (GRENOBLE)
Popular version of paper 3pAB4 “Automatic fish sounds classification”
Presented Wednesday afternoon, May 25, 2016, 2:15 in Salon I
171st ASA Meeting, Salt Lake City
In the current context of global warming and environmental concern, we need tools to evaluate and monitor the evolution of our environment. The evolution of animal populations is of a special concern in order to prevent changes of behaviour under environmental stress and to preserve biodiversity. Monitoring animal populations however, can be a complex and costly task. Experts can either (1) monitor animal populations directly on the field, or (2) use sensors to gather data on the field (audio or video recordings, trackers, etc.) and then process those data to retrieve knowledge about the animal population. In both cases the issue is the same: experts are needed and can only process limited quantity of data.
An alternative idea would be to keep using the field sensors but to build software tools in order to automatically process the data, thereby allowing monitoring animal populations on larger geographic areas and for extensive time periods.
The work we present is about automatically monitoring fish populations using audio recordings. Sounds have a better propagation underwater: by recording sounds under the sea we can gather loads of information about the environment and animal species it shelters. Here is an example of such recordings:
Legend: Raw recording of fish sounds, August 2014, Corsica, France.
Regarding fish populations, we distinguish four types of sounds that we call (1) Impulsions, (2) Roars, (3) Drums and (4) Quacks. We can hear them in the previous recording, but here are some extracts with isolated examples:
Legend: Filtered recording of fish sounds to hear Roar between 5s and 13s and Drums between 22s to 29s and 42s to 49s.
Legend: Filtered recording of fish sounds to hear Quacks and Impulsions. Both sounds are quite short (<0.5s) and are heard all along the recording.
However, to make a computer automatically classify a fish sound into one of those four groups is a very complex task. A simple or intuitive task for humans is often extremely complex for a computer, and vice versa. This is because humans and computers process information in different ways. For instance, a computer is very successful at solving complex calculations and at performing repetitive tasks, but it is very difficult to make a computer recognize a car in a picture. Humans however, tend to struggle with complex calculations but can very easily recognise objects in images. How do you explain a computer ‘this is a car’? It has four wheels. But then, how do you know this is a wheel? Well, it has a circular shape. Oh, so this ball is a wheel, isn’t it?
This easy task for a human is very complex for a machine. Scientists found a solution to make a computer understand what we call ‘high-level concepts’ (recognising objects in pictures, understanding speech, etc.). They designed algorithms called Machine Learning. The idea is to give a computer a lot of examples of each concept we want to teach it. For instance, to make a computer recognise a car in a picture, we feed it with many pictures of cars so that it can learn what a car is, and with many pictures without cars so that it can learn what a car is not. Many companies such as Facebook, Google, or Apple use those algorithms for face recognition, speech understanding, individualised advertisement, etc. It works very well.
In our work, we use the same technics to teach a computer to recognize and automatically classify fish sounds. Once those sounds have been classified, we can study their evolutions and see if fish populations behave differently from place to place, or if their behaviours evolve with time. It is also possible to study their density and see if their numbers vary through time.
This work is of a particular interest since to our knowledge, we present the first tool to automatically classify fish sounds. One of the main challenges is to make a sound understandable by a computer,that is to find and extract relevant information in the acoustic signal. By doing that, it gets easier for the computer to understand similarities and differences between all signals and in the end of the day, to be able to predict to which group a sound belongs.
Can a spider “sing”? If so, who might be listening?
Alexander L. Sweger – firstname.lastname@example.org
George W. Uetz – email@example.com
University of Cincinnati
Department of Biological Sciences
2600 Clifton Ave, Cincinnati OH 45221
Popular version of paper 4pAB3, “the potential for acoustic communication in the ‘purring’ wolf spider’
Presented Thursday afternoon, May 21, 2015, 2:40 PM, Rivers room
169th ASA Meeting, Pittsburgh
While we are familiar with a wide variety of animals that use sound to communicate- birds, frogs, crickets, etc.- there are thousands of animal species that use vibration as their primary means of communication. Since sound and vibration are physically very similar, the two are inextricable connected, but biologically they are still somewhat separate modes of communication. Within the field of bioacoustics, we are beginning to fully realize how prevalent vibration is as a mode of animal communication, and how interconnected vibration and sound are for many species.
Wolf spiders are one group that heavily utilizes vibration as a means of communication, and they have very sensitive structures for “listening” to vibrations. However, despite the numerous vibrations that are involved in spider communication, they are not known for creating audible sounds. While a lot of species that use vibration will simultaneously use airborne sound, spiders do not possess structures for hearing sound, and it is generally assumed that they do not use acoustic communication in conjunction with vibration.
The “purring” wolf spider (Gladicosa gulosa) may be a unique exception to this assumption. Males create vibrations when they communicate with potential mates in a manner very similar to other wolf spider species, but unlike other wolf spider species, they also create airborne sounds during this communication. Both the vibrations and the sounds produced by this species are of higher amplitude than other wolf spider species, both larger and smaller, meaning this phenomenon is independent of species size. While other acoustically communicating species like crickets and katydids have evolved structures for producing sound, these spiders are vibrating structures in their environment (dead leaves) to create sound. Since we know spiders do not possess typical “ears” for hearing these sounds, we are interested in finding out if females or other males are able to use these sounds in communication. If they do, then this species could be used as an unusual model for the evolution of acoustic communication.
Figure 1: An image of a male “purring” wolf spider, Gladicosa gulosa, and the spectrogram of his accompanied vibration. Listen to a recording of the vibration here,
and the accompanying sound here.
Our work has shown that the leaves themselves are vital to the use of acoustic communication in this species. Males can only produce the sounds when they are on a surface that vibrates (like a leaf) and females will only respond to the sounds when they are on a similar surface. When we remove the vibration and only provide the acoustic signal, females still show a significant response and males do not, suggesting that the sounds produced by males may play a part in communicating specifically with females.
So, the next question is- how are females responding to the airborne sound without ears? Despite the relatively low volume of the sounds produced, they can still create a vibration in a very thin surface like a leaf. This creates a complex method of communication- a male makes a vibration in a leaf that creates a sound, which then travels to another leaf and creates a new vibration, which a female can then hear. While relatively “primitive” compared to the highly-evolved acoustic communication in birds, frogs, insects, and other species, this unique usage of the environment may create opportunities for studying the evolution of sound as a mode of animal communication.
Peter M. Scheifele, Dept. of Communication Science, Univ. of Cincinnati, Cincinnati, OH 45267
A bleat is usually defined as the cry of a sheep or goat but they are just two voices in a large worldwide animal chorus that we are just starting to understand.
A bleat is a simple short burst of sound comprised of harmonic tones. It is easily voiced by young or small animals, who are the majority of the bleaters. From deer to polar bears; muskoxen to sea lions, the young bleats produce a sound of enough character to allow easy detection and possible identification by concerned mothers. As these animals mature usually their voices shift lower, longer, and louder and a vocabulary of other vocalizations are developed.
But for some notable exceptions this is not the case. For example, sheep and goats retain their bleating structure as their principal vocalization through adulthood – hence bleating is usually associated with them. Their bleats have been the most studied and show a characteristic varietal structure and at least a limited ability for maternal recognition of specific individuals.
For another example, at least four small varieties of toad, such as the Australian Bleating Toad and in America, the Eastern Narrow Mouthed Toad are strong bleaters through their entire life. Bleats provide them a signature signal that carries in the night and is easily repeatable and sustainable. But why these four amphibians? Our lack of an answer speaks to our still limited knowledge of the vast field of animal communication.
Perhaps most interestingly, the Giant Panda retains bleating while developing a complex mix of other vocalizations. It is probably the case that in the visually challenging environment of a dense bamboo thicket they must retain all possible vocal tools to communicate. Researchers link their bleating to male size and female age.
In summary, bleating is an important aspect of youth for many animals; for some it is the principal vocalization for life; and, for a few, a retained tool among many.