# Deep Representation Decomposition for Rate-Invariant Speaker Verification

arXiv: https://arxiv.org/abs/2205.14294 · HTML: https://mlsanity.com/paper/2205.14294/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2022.

## Built on by (most cited first, 2 of 2)

- [3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement](https://mlsanity.com/paper/2306.15354/) (2023)
- [LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention](https://mlsanity.com/paper/2506.02083/) (2025)

## Abstract (arXiv)

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker verification systems, which may actually degrade the system performance. To reduce intra-class discrepancy caused by speaking rate, we propose a deep representation decomposition approach with adversarial learning to learn speaking rate-invariant speaker embeddings. Specifically, adopting an attention block, we decompose the original embedding into an identity-related component and a rate-related component through multi-task training. Additionally, to reduce the latent relationship between the two decomposed components, we further propose a cosine mapping block to train the parameters adversarially to minimize the cosine similarity between the two decomposed components. As a result, identity-related features become robust to speaking rate and then are used for verification. Experiments are conducted on VoxCeleb1 data and HI-MIA data to demonstrate the effectiveness of our proposed approach.