---
license: openrail
language:
- en
metrics:
- f1
- recall
- accuracy
library_name: speechbrain
pipeline_tag: audio-classification
---
# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

We build a CTC-based phoneme recognition model using wav2vec 2.0 (W2V2) for children under 4-year-old. We use three-level fine-tuning to gradually reduce age mismatch between adult phonetics to child phonetics.

- **W2V2-Libri100h**: We first fine-tune W2V2-Base using 100 hours of LibriSpeech pretrained on unlabeled 960 hours LibriSpeech adult speech corpus with IPA phone sequences. 
- **W2V2-MyST**: We then fine-tune W2V2-Libri100h using [My Science Tutor](https://catalog.ldc.upenn.edu/LDC2021S05) corpus (consists of conversational speech of students between the third and fifth grades with a virtual tutor). 
- **W2V2-Libri100h-Pro (two-level fine-tuning)**: We fine-tune W2V2-Libri100h using [Providence](https://phonbank.talkbank.org/access/Eng-NA/Providence.html) corpus (consists of longititude audio of 6 English-speaking children aged from 1-4 years interacting with their mothers at home) on phoneme sequences.  
- **W2V2-MyST-Pro (three-level fine-tuning)**: Similar as W2V2-Libri100h-Pro, we fine-tune W2V2-MyST using Providence on phoneme sequences.  

We show W2V2-MyST-Pro is helpful for improving children's vocalization classification task on two corpus, including [Rapid-ABC](https://openaccess.thecvf.com/content_cvpr_2013/html/Rehg_Decoding_Childrens_Social_2013_CVPR_paper.html) and [BabbleCor](https://osf.io/rz4tx/). 

## Model Sources
For more information regarding this model, please checkout our paper:
- **[Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis](https://arxiv.org/abs/2309.07287)**
- **[Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations](https://arxiv.org/abs/2402.06888)**
  
## Model Description

<!-- Provide a longer summary of what this model is. -->
Folder contains the best checkpoint of the following setting
- **W2V2-Libri100h**: save_100h/wav2vec2.ckpt
- **W2V2-MyST**: save_100h_MyST/wav2vec2.ckpt
- **W2V2-Libri100h-Pro**: save_100h_Providence/wav2vec2.ckpt
- **W2V2-MyST-Pro**: save_100h_MyST_Providence/wav2vec2.ckpt

## Uses
**We develop our complete fine-tuning recipe using SpeechBrain toolkit available at**
[https://github.com/jialuli3/wav2vec_LittleBeats_LENA](https://github.com/jialuli3/wav2vec_LittleBeats_LENA)

<!-- 
- **https://github.com/jialuli3/speechbrain/tree/infant-voc-classification/recipes/RABC** (used for Rapid-ABC corpus)
- **https://github.com/jialuli3/speechbrain/tree/infant-voc-classification/recipes/Babblecor** (used for BabbleCor corpus)  
-->
# Paper/BibTex Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
If you found this model helpful to you, please cite us as
<pre><code>
@article{li2023enhancing,
  title={Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis},
  author={Li, Jialu and Hasegawa-Johnson, Mark and Karahalios, Karrie},
  booktitle={Interspeech},
  year={2024}
}
</code></pre>
and/or
<pre><code>
@inproceedings{li2024analysis,
  title={Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations},
  author={Li, Jialu and Hasegawa-Johnson, Mark and McElwain, Nancy L},
  booktitle={IEEE Workshop on Self-Supervision in Audio, Speech and Beyond (SASB)},
  year={2024}
}
</code></pre>

# Model Card Contact
Jialu Li, Ph.D. (she, her, hers)

E-mail: jialuli3@illinois.edu

Homepage: https://sites.google.com/view/jialuli/