Deep generative factorization for speech signal
This addresses a core difficulty in speech processing for applications requiring disentangled factors, though it appears incremental as it builds on existing flow-based methods.
The paper tackles the challenge of factorizing speech signals into distinct information factors like phonetic content and speaker traits by introducing a factorial discriminative normalization flow model (factorial DNF), which outperforms comparative models in representation and manipulation tasks.
Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks. An intuitive idea is to factorize speech signal into individual information factors (e.g., phonetic content and speaker trait), though it turns out to be highly challenging. This paper presents a speech factorization approach based on a novel factorial discriminative normalization flow model (factorial DNF). Experiments conducted on a two-factor case that involves phonetic content and speaker trait demonstrates that the proposed factorial DNF has powerful capability to factorize speech signals and outperforms several comparative models in terms of information representation and manipulation.