mlsanityData to 7 Oct 2026

Learnable Nonlinear Compression for Robust Speaker Verification

arXiv 2202.05236 ↗First posted 10 Feb 2022cs.SD cs.AI eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

In this study, we focus on nonlinear compression methods in spectral features for speaker verification based on deep neural network. We consider different kinds of channel-dependent (CD) nonlinear compression methods optimized in a data-driven manner. Our methods are based on power nonlinearities and dynamic range compression (DRC). We also propose multi-regime (MR) design on the nonlinearities, at improving robustness. Results on VoxCeleb1 and VoxMovies data demonstrate improvements brought by proposed compression methods over both the commonly-used logarithm and their static counterparts, especially for ones based on power function. While CD generalization improves performance on VoxCeleb1, MR provides more robustness on VoxMovies, with a maximum relative equal error rate reduction of 21.6%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 47 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

20 of 47 references.

References · 20

  1. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  2. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  3. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 606
  4. 2018Additive Margin Softmax for Face Verificationcited by 275
  5. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  6. 2020On the linearity of large non-linear models: when and why the tangent kernel is constantcited by 129
  7. 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 108
  8. 2020Speaker Recognition Based on Deep Learning: An Overviewcited by 59
  9. 2019Utterance-level Aggregation For Speaker Recognition In The Wildcited by 49
  10. 2019RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verificationcited by 33
  11. 2016Trainable Frontend For Robust and Far-Field Keyword Spottingcited by 32
  12. 2017Learning Filterbanks from Raw Speech for Phone Recognitioncited by 25
8 more
  1. 2019VoxSRC 2019: The first VoxCeleb Speaker Recognition Challengecited by 13
  2. 2020Playing a Part: Speaker Verification at the Moviescited by 11
  3. 2019VoiceID Loss: Speech Enhancement for Speaker Verificationcited by 10
  4. 2021Learnable MFCCs for Speaker Verificationcited by 6
  5. 2020NPLDA: A Deep Neural PLDA Model for Speaker Verificationcited by 4
  6. 2021Towards Robust Speaker Verification with Target Speaker Enhancementcited by 4
  7. 2021Sound Event Detection in Urban Audio With Single and Multi-Rate PCENcited by 3
  8. 2021Parameterized Channel Normalization for Far-field Deep Speaker Verificationcited by 1

Built on by

Not cited yet.