Whisper-Base for Child Vocalization Classification (ReCANVo Dataset)
Model Description
This model includes the implementation of child speech vocalization classification described in ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood (Accepted to EMNLP 2026 Main)
Github repository: https://github.com/tiantiaf0627/childvox-release
The model is fine-tuned on the ReCANVo dataset, a large-scale corpus of child vocalizations (including young adults too).
The included child vocalization categories are:
[
"delighted",
"dysregulated",
"frustrated",
"request",
"self-talk",
"social",
]
How to use this model
Download repo
git clone git@github.com:tiantiaf0627/childvox-release
Install the package
conda create -n childvox python=3.10
cd childvox
pip install -e .
Load the model
# Load libraries
import torch
import torch.nn.functional as F
from src.model.childvox.whisper_audio import WhisperWrapper
# Find device
device = torch.device("cuda") if torch.cuda.is_available() else "cpu"
# Load model from Huggingface
# We provide model with different folds, and specify the fold from 1, 2, 3, 4, 5
model = WhisperWrapper.from_pretrained("tiantiaf/childvox-ReCANVo-whisper-base", fold_idx=1).to(device)
model.eval()
Prediction
# Label List
label_list = [
"delighted",
"dysregulated",
"frustrated",
"request",
"self-talk",
"social",
]
# Load data, here just zeros as the example
# The child vocalization segments used in training are short, so we cap the input at 5 seconds
# You need to prepare your audio to a length of 5 seconds, 16kHz and mono channel
max_audio_length = 5 * 16000
data = torch.zeros([1, 160000]).float().to(device)[:, :max_audio_length]
logits, embeddings = model(data, return_feature=True)
# Probability and output
maturity_prob = F.softmax(logits, dim=1)
print(label_list[torch.argmax(maturity_prob).detach().cpu().item()])
Responsible Use: Child speech data is highly sensitive. Users should respect the privacy and consent of the children and families whose recordings are processed, obtain approval from the appropriate ethics/IRB body, and adhere to the relevant laws and regulations in their jurisdictions when using ChildVox.
If you have any questions, please contact: Tiantian Feng (tiantiaf@usc.edu)
❌ Out-of-Scope Use
- Clinical or diagnostic applications (e.g., screening for developmental or language disorders)
- Individual-level developmental assessment without expert human review
- Surveillance
- Privacy-invasive applications
- No commercial use
If you like our work or use the models in your work, kindly cite the following. We appreciate your recognition!
@article{feng2026childvox,
title={ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood},
author={Feng, Tiantian and Xu, Anfeng and Shi, Xuan and Kommineni, Aditya and Siam, Shakhrul Iman and Micheletti, Megan and Shi, Zhonghao and Tager-Flusberg, Helen and Zhang, Mi and Perry, Lynn K and others},
journal={arXiv preprint arXiv:2605.29257},
year={2026}
}
Please also cite the following dataset if you use this model:
@article{johnson2023recanvo,
title={ReCANVo: A database of real-world communicative and affective nonverbal vocalizations},
author={Johnson, Kristina T and Narain, Jaya and Quatieri, Thomas and Maes, Pattie and Picard, Rosalind W},
journal={Scientific Data},
volume={10},
number={1},
pages={523},
year={2023},
publisher={Nature Publishing Group UK London}
}