%0 Generic %1 hedeshy2024audio %A Hedeshy, Ramin %A Menges, Raphael %A Staab, Steffen %D 2024 %K darus ubs_10005 ubs_20008 ubs_30082 ubs_40488 unibibliografie %R 10.18419/darus-3897 %T Raw audio samples of the CNVVE dataset %X This CNVVE Dataset contains raw audio samples encompassing six distinct classes of voice expressions, namely “Uh-huh” or “mm-hmm”, “Uh-uh” or“mm-mm”, “Hush” or “Shh”, “Psst”, “Ahem”, and Continuous humming, e.g., “hmmm.” Audio samples of each class are found in the respective folders. The samples are recorded through a dedicated website for data collection that defines the purpose and type of voice data by providing example recordings to participants as well as the expressions’ written equivalent, e.g., “Uh-huh”. Audio recordings were automatically saved in the .wav format and kept anonymous, with a sampling rate of 48 kHz and a bit depth of 32 bits.This dataset contains a raw version of the samples. A cleaned version of these samples can be found on https://doi.org/10.18419/darus-3898. For more info, please check the paper or feel free to contact the authors for any inquiries.

@misc{hedeshy2024audio, abstract = {This CNVVE Dataset contains raw audio samples encompassing six distinct classes of voice expressions, namely “Uh-huh” or “mm-hmm”, “Uh-uh” or“mm-mm”, “Hush” or “Shh”, “Psst”, “Ahem”, and Continuous humming, e.g., “hmmm.” Audio samples of each class are found in the respective folders. The samples are recorded through a dedicated website for data collection that defines the purpose and type of voice data by providing example recordings to participants as well as the expressions’ written equivalent, e.g., “Uh-huh”. Audio recordings were automatically saved in the .wav format and kept anonymous, with a sampling rate of 48 kHz and a bit depth of 32 bits.This dataset contains a raw version of the samples. A cleaned version of these samples can be found on https://doi.org/10.18419/darus-3898. For more info, please check the paper or feel free to contact the authors for any inquiries. }, added-at = {2024-02-19T15:14:11.000+0100}, affiliation = {Hedeshy, Ramin/Universität Stuttgart, Menges, Raphael/Semanux, Staab, Steffen/Universität Stuttgart}, author = {Hedeshy, Ramin and Menges, Raphael and Staab, Steffen}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/233be79b0337a02ba0883e7d757ef11a9/unibiblio}, doi = {10.18419/darus-3897}, howpublished = {Dataset}, interhash = {93e6457b7e948a839dd8d92a43b119ba}, intrahash = {33be79b0337a02ba0883e7d757ef11a9}, keywords = {darus ubs_10005 ubs_20008 ubs_30082 ubs_40488 unibibliografie}, note = {Related to: CNVVE: Dataset and Benchmark for Classifying Non-verbal Voice Expressions.R. Hedeshy, R. Menges, and S. Staab. Interspeech 2023, August 20-24, 2023. Dublin, Ireland, (2023). doi: 10.21437/Interspeech.2023-201}, orcid-numbers = {Hedeshy, Ramin/0000-0001-5854-4033, Menges, Raphael/0000-0002-2112-7065, Staab, Steffen/0000-0002-0780-4154}, timestamp = {2024-02-26T09:44:56.000+0100}, title = {Raw audio samples of the CNVVE dataset}, year = 2024 }