Bayesian adaptive learning to latent variables via Variational Bayes and Maximum a Posteriori

Hu Hu, Sabato Marco Siniscalchi, Chin-Hui LeearXiv 2024 · DOI · arXiv

Introduction

Acoustic scene classification (ASC) systems often face performance degradation when deployed on devices different from those used during training, a phenomenon known as "device mismatch." This occurs because hardware variations—specifically microphone characteristics and signal processing pipelines—create an acoustic gap between training (source) and deployment (target) devices. Standard adaptation techniques, such as fine-tuning on limited target data, often fail to capture the underlying structural relationships between domains. This work addresses device adaptation by mathematically adjusting a pre-trained source model using a Bayesian framework centered on latent variables.

Methodology

The proposed framework focuses on the latent variables ($Z$) within a Deep Neural Network (DNN), representing intermediate embeddings between input features and final classification outputs. The core principle is to treat the source domain's latent variables as a prior distribution, which is then updated using the likelihood of the target data to derive a posterior distribution.

Two primary approaches are explored:

  1. Bayesian Adaptation via Variational Bayes (BA-VB): This method approximates the full posterior distribution of latent variables using a Gaussian mean-field approximation, minimizing the Kullback-Leibler (KL) divergence between the estimated and true distributions.
  2. Bayesian Adaptation via Maximum a Posteriori (BA-MAP): A point-estimation approach that incorporates prior knowledge. The authors demonstrate that under a Dirichlet assumption for latent variables (soft outputs), BA-MAP becomes equivalent to Teacher-Student (TS) learning.

Experimental Setup

The methods were evaluated using the DCASE 2020 Challenge Task 1a dataset. The source data consisted of approximately 10,000 audio clips from "Device A," while the target data included 750 clips for each of eight different devices (Device B, C, and s1-s6). The dataset features parallel recordings, where the same acoustic scene was captured simultaneously by different hardware, providing a robust ground truth for comparison.

Results and Analysis

The Bayesian methods demonstrated superior performance compared to baseline and state-of-the-art transfer learning techniques. As shown in the results table below, the BA-VB approach achieved the highest average accuracy.

Comparison of average accuracy across different transfer learning methods.

The BA-VB method provided a 14.47% absolute improvement over the "No transfer" baseline and outperformed specialized algorithms like Relational Knowledge Distillation (RKD) and Selective Pseudo-labeling (SP). The success of BA-VB suggests that modeling the full distribution of latent variables, rather than a single point estimate, provides greater robustness against the noise and hardware variations inherent in different recording devices.

Conclusion

This paper introduces a principled Bayesian framework for device adaptation in acoustic scene classification. By treating intermediate representations as latent variables and employing Variational Bayes, the researchers successfully bridged the performance gap caused by device mismatch. While BA-VB is more computationally intensive than MAP due to the sampling required by the reparameterization trick, its performance gains are significant. Future work will investigate the scalability of this approach to larger tasks and its performance in non-parallel data scenarios.

Summary updated

Abstract

In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and structural relationships. Thus the distributions of the source latent variables (prior) can be combined with the knowledge learned from the target data (likelihood) to yield the distributions of the target latent variables (posterior) with the goal of addressing acoustic mismatches between training and testing conditions. The prior knowledge transfer is accomplished through Variational Bayes (VB). In addition, we also investigate Maximum a Posteriori (MAP) based Bayesian adaptation. Experimental results on device adaptation in acoustic scene classification show that our proposed approaches can obtain good improvements on target devices, and consistently outperforms other cut-edging algorithms.
BibTeX
@misc{hu2024bayesian,
  author = {Hu Hu and Sabato Marco Siniscalchi and Chin-Hui Lee},
  title = {{Bayesian adaptive learning to latent variables via Variational Bayes and Maximum a Posteriori}},
  year = {2024},
  eprint = {2401.13766},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.13766},
}
Figure