mlsanityData to 7 Oct 2026

Improved far-field speech recognition using Joint Variational Autoencoder

arXiv 2204.11286 ↗First posted 24 Apr 2022eess.AS cs.CL cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 30 references that are in the map. First posted on arXiv 24 Apr 2022.

Builds on

9 of 30 references.

References · 9

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2017Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Datacited by 92
  4. 2017Learning Latent Representations for Speech Generation and Transformationcited by 27
  5. 2017Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentationcited by 27
  6. 2018Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognitioncited by 5
  7. 2018A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognitioncited by 4
  8. 2017Speech Dereverberation Using Nonnegative Convolutive Transfer Function and Spectro temporal Modelingcited by 3
  9. 2018On the use of DNN Autoencoder for Robust Speaker Recognitioncited by 2

Built on by

Not cited yet.