Learning Disentangled Audio Representations through Controlled Synthesis

This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques. Benchmarking state-of-the-art methods on SynTone highlights its utility for method evaluation. Our results underscore strengths and limitations in audio disentanglement, motivating future research.

Learning Disentangled Speech Representations

Disentangled representation learning from speech remains limited despite its importance in many application domains. A key challenge is the lack of speech datasets with known generative factors to evaluate methods. This paper proposes SynSpeech: a novel synthetic speech dataset with ground truth factors enabling research on disentangling speech representations. We plan to present a comprehensive study evaluating supervised techniques using established supervised disentanglement metrics. This benchmark dataset and framework address the gap in the rigorous evaluation of state-of-the-art disentangled speech representation learning methods. Our findings will provide insights to advance this underexplored area and enable more robust speech representations.

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

The choice of the objective function is crucial in emerging high-quality representations from self-supervised learning. This paper investigates how different formulations of the Barlow Twins (BT) objective impact downstream task performance for speech data. We propose Modified Barlow Twins (MBT) with normalized latents to enforce scale-invariance and evaluate on speaker identification, gender recognition and keyword spotting tasks. Our results show MBT improves representation generalization over original BT, especially when fine-tuning with limited target data. This highlights the importance of designing objectives that encourage invariant and transferable representations. Our analysis provides insights into how the BT learning objective can be tailored to produce speech representations that excel when adapted to new downstream tasks. This study is an important step towards developing reusable self-supervised speech representations.