CONCORD, MA, October 26, 2009 – Wildlife Acoustics, the leading supplier of acoustic monitoring systems for endangered and threatened wildlife species around the world, announces the production availability of the new Song Meter SM2 autonomous audio recorder and data logging platform. Designed for the rugged demands of habitats from tropical to arctic, the SM2 combines extremely low power consumption, high capacity, and sophisticated scheduling for long-term field deployments. The new platform delivers integrated acoustic monitoring and data logging in a cost- effective, weatherproof and expandable design.
“Species extinction rates are hundreds of times greater than at any time in the history of the earth. Monitoring threatened populations is essential for understanding the effects of climate change and to measure the impact of the corrective actions we take.” stated Ian Agranat, President of Wildlife Acoustics. “With thousands of units in the field, we now make it easier and more affordable for scientists to track and monitor areas that were too expensive to cover in the past by labor-intensive point counts surveys.”
The new Song Meter SM2 is a powerful and expandable platform that is a significant improvement for our current core users who track birds and frogs in remote and isolated locations and is now capable of a greater range of applications ranging from ultrasonic bat detection for the wind farm industry to underwater acoustic monitoring of fish and cetaceans.
Song Meter SM2 New Features:
Terrestrial Acoustic monitoring:
The SM2 Terrestrial Acoustic Package is optimized for monitoring birds, frogs, and other terrestrial wildlife vocalizing in the audio (20-20,000Hz) frequency range. The package includes the new SM2 expandable platform equipped with two removable weatherproof and highly sensitive omni-directional SMX-II microphones. With just 4 D-size batteries, SM2 can record up to 250 hours on a programmable schedule spread out through several months at a time. Longer deployments are also possible with an optional external power source. The recorder includes a built-in temperature sensor and data-logger, and can accept a second analog sensor input to monitor other environmental conditions such as soil temperature, water level, rainfall, etc.
About Wildlife Acoustics, Inc.
A wildly innovative company.
Wildlife Acoustics, Inc., a privately held Massachusetts corporation, is the leading provider of bio-acoustic monitoring technology for scientists, researchers, and government agencies worldwide since 2003.
Wildlife Acoustics, Inc.
P. O. Box 680
Concord, MA 01742-0680
+1 (978) 369-5225
Commercially available autonomous recorders for monitoring vocal wildlife populations such as birds and frogs now make it possible to collect thousands of hours of audio data in a field season. Given limited resources, it is not practical to manually review this volume of data “by ear”. The automatic processing of sound recordings to detect and identify specific species from their vocalizations, even if not perfectly accurate, makes efficient use of researchers who review only those samples most likely to contain vocalizations of interest. This results in significant gains of sample coverage, operating efficiency, and cost savings.
Developing generalized computer algorithms capable of accurate species identification in real-world field conditions is full of difficult challenges. First, recordings made by autonomous recorders typically receive sounds from all directions, scattered and reflected by trees, obscured by an unpredictable constellation of random noise, wind, rustling leaves, airplanes, road traffic, and other species of birds, frogs, insects and mammals. Second, the vocalizations of many species are highly varied from one individual to the next. Any algorithm must be prepared to accept vocalizations that are similar, but not identical, to known references in order to successfully detect the previously unobserved individual. However, in so doing, the algorithm is then susceptible to misclassifying a vocalization from a different species with similar components. This is especially true for species with narrowband vocalizations lacking distinctive spectral properties and in species with short duration vocalizations lacking distinctive temporal properties.
The bulk of prior research has generally differentiated among only a handful of simple mono-syllabic vocalizations at a time. While the results have been promising, we found that many approaches degrade significantly as the number of species increases, especially when more complex multi-syllabic and highly variable vocalizations are also included.
In this paper, we discuss an algorithm based on Hidden Markov Models automatically constructed so as to consider not just the spectral and temporal features of individual syllables, but also how syllables are organized into more complex songs. Additionally, several techniques are employed to reduce the effects of noise present in recordings made by autonomous recorders.