# Toward Corpus Size Requirements for Training and Evaluating Depression Risk Models Using Spoken Language

arXiv: https://arxiv.org/abs/2501.00617 · HTML: https://mlsanity.com/paper/2501.00617/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 31 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Semi-supervised Sequence Learning](https://mlsanity.com/paper/1511.01432/) (2015)
- [AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition](https://mlsanity.com/paper/1907.11510/) (2019)
- [Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Model](https://mlsanity.com/paper/2202.08210/) (2022)
- [Remote smartphone-based speech collection: acceptance and barriers in individuals with major depressive disorder](https://mlsanity.com/paper/2104.08600/) (2021)
- [Speech-Based Depression Prediction Using Encoder-Weight-Only Transfer Learning and a Large Corpus](https://mlsanity.com/paper/2412.16900/) (2024)
- [Depression and Anxiety Prediction Using Deep Language Models and Transfer Learning](https://mlsanity.com/paper/2412.20741/) (2024)

## Built on by (most cited first, 1 of 1)

- [A multimodal Bayesian Network for symptom-level depression and anxiety prediction from voice and speech data](https://mlsanity.com/paper/2512.07741/) (2025)

## Abstract (arXiv)

Mental health risk prediction is a growing field in the speech community, but many studies are based on small corpora. This study illustrates how variations in test and train set sizes impact performance in a controlled study. Using a corpus of over 65K labeled data points, results from a fully crossed design of different train/test size combinations are provided. Two model types are included: one based on language and the other on speech acoustics. Both use methods current in this domain. An age-mismatched test set was also included. Results show that (1) test sizes below 1K samples gave noisy results, even for larger training set sizes; (2) training set sizes of at least 2K were needed for stable results; (3) NLP and acoustic models behaved similarly with train/test size variations, and (4) the mismatched test set showed the same patterns as the matched test set. Additional factors are discussed, including label priors, model strength and pre-training, unique speakers, and data lengths. While no single study can specify exact size requirements, results demonstrate the need for appropriately sized train and test sets for future studies of mental health risk prediction from speech and language.