datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
mouse-identity-classification-benchmark
VocSim — Mouse Identity Classification
A companion dataset for the VocSim benchmark that tests whether audio embeddings preserve individual identity in mouse ultrasonic vocalizations (USVs). It contains pre-segmented USV syllables from multiple individual mice (the speaker field), sampled at the native 250 kHz, derived from recordings by Van Segbroeck et al. (2017).
Basha, M., Zai, A. T., Stoll, S., & Hahnloser, R. H. R. VocSim: A Training-free Benchmark for Zero-shot Content… See the full description on the dataset page: https://huggingface.co/datasets/vocsim/mouse-identity-classification-benchmark.mouse-strain-classification-benchmark
VocSim — Mouse Strain Classification
A companion dataset for the VocSim benchmark that tests whether audio embeddings preserve strain identity in mouse ultrasonic vocalizations (USVs). It contains pre-segmented USV syllables from C57BL/6J (C57) and DBA/2J (DBA) mice, sampled at the native 250 kHz so high-frequency structure is preserved.
Basha, M., Zai, A. T., Stoll, S., & Hahnloser, R. H. R. VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source… See the full description on the dataset page: https://huggingface.co/datasets/vocsim/mouse-strain-classification-benchmark.vad-mouse
Positive Transfer Of The Whisper Speech Transformer To Human And Animal Voice Activity Detection
We proposed WhisperSeg, utilizing the Whisper Transformer pre-trained for Automatic Speech Recognition (ASR) for both human and animal Voice Activity Detection (VAD). For more details, please refer to our paper
Positive Transfer of the Whisper Speech Transformer to Human and Animal Voice Activity Detection
Nianlong Gu, Kanghwi Lee, Maris Basha, Sumit Kumar Ram, Guanghao You, Richard H.… See the full description on the dataset page: https://huggingface.co/datasets/nccratliri/vad-mouse.common_voice_19_uk_croppedstepik_ml_ru