Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations
This work improves utterance-level speech processing for applications like speaker and emotion recognition, representing an incremental advance by enhancing existing self-supervised methods.
The paper tackled the problem of poor performance of self-supervised speech models on utterance-level tasks like speaker and emotion recognition by addressing the lack of disentangled representations and utterance-level objectives, resulting in models that outperform the best existing model, WavLM, on all non-semantic tasks in the SUPERB benchmark using only 20% labeled data.
Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition (ASR) and proved to be extremely useful in low label-resource settings. However, the success of SSL models has yet to transfer to utterance-level tasks such as speaker, emotion, and language recognition, which still require supervised fine-tuning of the SSL models to obtain good performance. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective for these tasks. Inspired by how HuBERT uses clustering to discover hidden acoustic units, we formulate a factor analysis (FA) model that uses the discovered hidden acoustic units to align the SSL features. The underlying utterance-level representations are disentangled from the content of speech using probabilistic inference on the aligned features. Furthermore, the variational lower bound derived from the FA model provides an utterance-level objective, allowing error gradients to be backpropagated to the Transformer layers to learn highly discriminative acoustic units. When used in conjunction with HuBERT's masked prediction training, our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.