---
base_model:
- MarvinLvn/BabyHuBERT
datasets:
- BabbleCor
language:
- multilingual
license: openrail
metrics:
- f1
- accuracy
pipeline_tag: audio-classification
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
- child_speech
- child_vocalization
- speech_maturity
library_name: transformers
---

# BabyHuBERT for Child Speech Maturity (BabbleCor Corpus) Classification

# Model Description
This model includes the implementation of child speech maturity classification described in <a href="https://arxiv.org/abs/2605.29257"><strong>**ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood**</strong></a> (Accepted to EMNLP 2026 Main)

Github repository: https://github.com/tiantiaf0627/childvox-release

The model is fine-tuned on the **BabbleCor** dataset, a large-scale corpus of child vocalizations.

The included child vocalization categories are:
```
[
  'Canonical',
  'Non-Canonical',
  'Crying',
  'Laughing',
  'Junk'
]
```

`Canonical` denotes mature syllables containing a consonant-vowel transition, while `Non-Canonical` denotes immature vocalizations such as isolated vowels or consonants. `Junk` covers segments that are not child vocalizations (e.g., noise, adult speech, or unintelligible audio).

# How to use this model

## Download repo
```bash
git clone git@github.com:tiantiaf0627/childvox-release
```
## Install the package
```bash
conda create -n childvox python=3.10
cd childvox
pip install -e .
```

## Load the model
```python
# Load libraries
import torch
import torch.nn.functional as F
from src.model.childvox.babyhubert_audio import BabyHuBERTWrapper

# 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 = BabyHuBERTWrapper.from_pretrained("tiantiaf/childvox-babblecor-babyhubert", fold_idx=1).to(device)
model.eval()
```

## Prediction
```python
# Label List
maturity_list = [
  'Canonical',
  'Non-Canonical',
  'Crying',
  'Laughing',
  'Junk'
]

# Load data, here just zeros as the example
# The child vocalization segments used in training are short, so we cap the input at 1 seconds
# You need to prepare your audio to a length of 1 seconds, 16kHz and mono channel
max_audio_length = 1 * 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(maturity_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}
}
```