# Learnable MFCCs for Speaker Verification

arXiv: https://arxiv.org/abs/2102.10322 · HTML: https://mlsanity.com/paper/2102.10322/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 20 Feb 2021.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [MelNet: A Generative Model for Audio in the Frequency Domain](https://mlsanity.com/paper/1906.01083/) (2019)
- [Learning Filterbanks from Raw Speech for Phone Recognition](https://mlsanity.com/paper/1711.01161/) (2017)
- [Filterbank design for end-to-end speech separation](https://mlsanity.com/paper/1910.10400/) (2019)
- [The BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF](https://mlsanity.com/paper/1304.2865/) (2013)
- [A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings](https://mlsanity.com/paper/2007.15283/) (2020)
- [Multi-Task Learning with High-Order Statistics for X-vector based Text-Independent Speaker Verification](https://mlsanity.com/paper/1903.12058/) (2019)

## Built on by (most cited first, 6 of 6)

- [Machine Learning for Stuttering Identification: Review, Challenges and Future Directions](https://mlsanity.com/paper/2107.04057/) (2021)
- [Parameterized Channel Normalization for Far-field Deep Speaker Verification](https://mlsanity.com/paper/2109.12056/) (2021)
- [Learnable Nonlinear Compression for Robust Speaker Verification](https://mlsanity.com/paper/2202.05236/) (2022)
- [Optimizing Multi-Taper Features for Deep Speaker Verification](https://mlsanity.com/paper/2110.10983/) (2021)
- [Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?](https://mlsanity.com/paper/2310.09806/) (2023)
- [Optimising MFCC parameters for the automatic detection of respiratory diseases](https://mlsanity.com/paper/2408.07522/) (2024)

## Abstract (arXiv)

We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification. Our architecture retains the simplicity and interpretability of MFCC-based features while allowing the model to be adapted to data flexibly. In practice, we formulate data-driven versions of the four linear transforms of a standard MFCC extractor -- windowing, discrete Fourier transform (DFT), mel filterbank and discrete cosine transform (DCT). Results reported reach up to 6.7% (VoxCeleb1) and 9.7% (SITW) relative improvement in term of equal error rate (EER) from static MFCCs, without additional tuning effort.