Foundation Model Hidden Representations for Heart Rate Estimation from Auscultation
AuthorsJingping Nie†‡, Tien Dung Tran, Karan Thakkar§‡, Vasudha Kowtha, Jon Huang, Carlos Avendano, Erdin Azemi, Vikramjit Mitra
AuthorsJingping Nie†‡, Tien Dung Tran, Karan Thakkar§‡, Vasudha Kowtha, Jon Huang, Carlos Avendano, Erdin Azemi, Vikramjit Mitra
Auscultation, particularly heart sound, is a non-invasive technique that provides essential vital sign information. Recently, self-supervised acoustic representation founda- tion models (FMs) have been proposed to offer insights into acoustics-based vital signs. However, there has been little exploration of the extent to which auscultation is encoded in these pre-trained FM representations. In this work, using a publicly available phonocardioram (PCG) dataset and a heart rate (HR) estimation model, we con- duct a layer-wise investigation of six acoustic representa- tion FMs: HuBERT, wav2vec2, wavLM, Whisper, Con- trastive Language-Audio Pretraining (CLAP), and an in- house CLAP model. Additionally, we implement the baseline method from [1] (which relies on acoustic fea- tures), and show that overall, representation vectors from pre-trained foundation models (FMs) offer comparable performance to the baseline. Notably, HR estimation using the representations from the audio encoder of the in-house CLAP model outperforms the results obtained from the baseline, achieving a lower mean absolute error (MAE) across various train/validation/test splits despite the domain mismatch.
August 1, 2024research area Data Science and Annotation, research area Health
This paper has been accepted at IEEE International Workshop on Machine Learning for Signal Process (MLSP) 2024.
Acoustic signals are crucial for health monitoring, particularly heart sounds which provide essential data like heart rate and detect cardiac anomalies such as murmurs. This study utilizes a publicly available phonocardiogram (PCG) dataset to estimate heart rate using model-driven methods and extends the best-performing model to a...
March 14, 2023research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSP
Pre-trained model representations have demonstrated state-of-the-art performance in speech recognition, natural language processing, and other applications. Speech models, such as Bidirectional Encoder Representations from Transformers (BERT) and Hidden units BERT (HuBERT), have enabled generating lexical and acoustic representations to benefit speech recognition applications. We investigated the use of pre-trained model representations for...