mlsanityData to 19 Oct 2026

Multiple Confidence Gates For Joint Training Of SE And ASR

arXiv 2204.00226 ↗First posted 1 Apr 2022eess.AScited by 0

On the map: Speech and audio language models → Speech enhancement and noise suppression

Abstract (arXiv)

Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is changed, which is uncertain and detrimental to the ASR. To tackle this challenge, an approach with multiple confidence gates for jointly training of SE and ASR is proposed. A speech confidence gates prediction module is designed to replace the former SE module in joint training. The noisy speech is filtered by gates to obtain features that are easier to be fitting by the ASR network. The experimental results show that the proposed method has better performance than the traditional robust speech recognition system on test sets of clean speech, synthesized noisy speech, and real noisy speech.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 15 of its 25 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

15 of 25 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement26 Aug
  2. 2021An Investigation of End-to-End Models for Robust Speech Recognition11 Feb

Other references · 13

  1. 2014Adam: A Method for Stochastic Optimizationcited by 38,210
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,093
  3. 2016Layer Normalizationcited by 5,866
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,653
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 2,293
  6. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 694
  7. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 497
  8. 2015LSTM: A Search Space Odysseycited by 321
  9. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 284
  10. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 147
  11. 2020Improving noise robust automatic speech recognition with single-channel time-domain enhancement networkcited by 45
  12. 2020Data augmentation and loss normalization for deep noise suppressioncited by 42
1 more
  1. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Frameworkcited by 30

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Bridging the Gap: Integrating Pre-trained Speech Enhancement and Recognition Models for Robust Speech Recognition
  2. 2022Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR
  3. 2021Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement
  4. 2021Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
  5. 2021Training Speech Enhancement Systems with Noisy Speech Datasets
  6. 2024Towards Decoupling Frontend Enhancement and Backend Recognition in Monaural Robust ASR
  7. 2021SNRi Target Training for Joint Speech Enhancement and Recognition
  8. 2025Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning