# Improved far-field speech recognition using Joint Variational Autoencoder

arXiv: https://arxiv.org/abs/2204.11286 · HTML: https://mlsanity.com/paper/2204.11286/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 24 Apr 2022.

## Builds on (most cited first, 9 of 9)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [Learning Latent Representations for Speech Generation and Transformation](https://mlsanity.com/paper/1704.04222/) (2017)
- [Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation](https://mlsanity.com/paper/1707.06265/) (2017)
- [Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition](https://mlsanity.com/paper/1803.02551/) (2018)
- [A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition](https://mlsanity.com/paper/1806.04841/) (2018)
- [Speech Dereverberation Using Nonnegative Convolutive Transfer Function and Spectro temporal Modeling](https://mlsanity.com/paper/1709.05557/) (2017)
- [On the use of DNN Autoencoder for Robust Speaker Recognition](https://mlsanity.com/paper/1811.02938/) (2018)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) systems suffer considerably when source speech is corrupted with noise or room impulse responses (RIR). Typically, speech enhancement is applied in both mismatched and matched scenario training and testing. In matched setting, acoustic model (AM) is trained on dereverberated far-field features while in mismatched setting, AM is fixed. In recent past, mapping speech features from far-field to close-talk using denoising autoencoder (DA) has been explored. In this paper, we focus on matched scenario training and show that the proposed joint VAE based mapping achieves a significant improvement over DA. Specifically, we observe an absolute improvement of 2.5% in word error rate (WER) compared to DA based enhancement and 3.96% compared to AM trained directly on far-field filterbank features.