Multi-site environmental field recordings for audio event recognition in Upstate NY

The first soundscape is located in a lightly wooded suburban area north of Albany, New York, at about 100 meters above sea level. The surrounding vegetation consists of white pines, spruces, oaks, and maples. The acoustic data was originally collected using a Zoom H2n Handy Recorder in 4-channel mode, yet only data from a single microphone capsule is presented.. Recordings were originally made at 16 bits in Waveform Audio File Format (WAV) at a frequency of 44,100 Hz. This dataset was collected from August 2019 to August 2020. The second soundscape is located in a forested area in Lake George, New York, also at about 100 meters above sea level. The surrounding vegetation consists largely of white pines. The microphone array consisted of two H2n Zoom recorders mounted perpendicularly to simulate four-channel recording conditions, yet only data from a single microphone capsule is presented. Recordings were originally made at 256 kbps in MPEG-2 Audio Layer III (MP3) format. This dataset was collected from February 2020 until February 2021. Once all of the audio data was collected, it was segmented into 8 second-long clips, to ensure that both biological and anthropogenic sound sources with longer call lengths were provided with sufficient temporal context, while still achieving reasonable computational efficiency. Each segment was then downsampled to 16 kHz for processing efficiency, allowing each to be represented as a 128,000-sample vector. Sounds ECMK- Eastern chipmunk "chuck" DGBR- dog bark DOWO- Downy woodpecker drum RNFL- rainfall ENGE- engine RCCR- remote control car BUBP- back-up beeper (truck) SREN- siren FFCR- fall field cricket DDCC- dog-day cicada ECMC- Eastern chipmunk "chirp" EGSK- Eastern gray squirrel "kuk" AMRO- American robin AMCR- American crow BLJA- Bluejay NOCA- Northern cardinal BCCH- Black-capped chickadee EAPH- Eastern phoebe BAWW- Black-and-white warbler WBNU- White-breasted nuthatch RBNU- Red-breasted nuthatch **Sounds from site 1 have no specific label tag while sounds from site 2 are specifically labeled with "-site2"