English

Deep generative factorization for speech signal

Sound 2020-10-28 v1 Machine Learning Audio and Speech Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2010.14242,
  title  = {Deep generative factorization for speech signal},
  author = {Haoran Sun and Lantian Li and Yunqi Cai and Yang Zhang and Thomas Fang Zheng and Dong Wang},
  journal= {arXiv preprint arXiv:2010.14242},
  year   = {2020}
}

Comments

Submitted to ICASSP 2021

R2 v1 2026-06-23T19:41:03.728Z