mlsanityData to 7 Oct 2026

Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data

arXiv 2203.15321 ↗First posted 29 Mar 2022cs.SD cs.CL eess.AScited by 30

Not on the map. Why?

Abstract (arXiv)

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such plenty of in-domain data is not always available in the real-life world. In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (Simu-GAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. Furthermore, we also propose a dual-path speech recognition system to improve the robustness of the system under noisy conditions. Experimental results show that the proposed speech recognition system achieves 7.3% absolute improvement with simulated noisy data by Simu-GAN over the best baseline in terms of word error rate (WER).

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

13 of 20 references.

References · 13

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  4. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  6. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  7. 2017Generative Adversarial Networks: An Overviewcited by 588
  8. 2015Listen, Attend and Spellcited by 542
  9. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  10. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
  11. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  12. 2018StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networkscited by 78
1 more
  1. 2021Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speechcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 11; 2024: 9; 2025: 3; 2026: 3.

30 papers.

Sort:

By area:

  1. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
  2. 2024GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translatorscited by 22
  3. 2022Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learningcited by 21
  4. 2024Speech Robust Bench: A Robustness Benchmark For Speech Recognitioncited by 20
  5. 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
  6. 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 16
  7. 2023Fairness-Aware Client Selection for Federated Learningcited by 15
  8. 2024Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Modelscited by 13
  9. 2023Metric-oriented Speech Enhancement using Diffusion Probabilistic Modelcited by 11
  10. 2023Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separationcited by 10
  11. 2023Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognitioncited by 10
  12. 2023Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASRcited by 10
18 more
  1. 2023Unsupervised Noise adaptation using Data Simulationcited by 9
  2. 2023Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognitioncited by 9
  3. 2024Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentationcited by 9
  4. 2022Self-critical Sequence Training for Automatic Speech Recognitioncited by 8
  5. 2023Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognitioncited by 7
  6. 2024Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Modelscited by 7
  7. 2022Speech-text based multi-modal training with bidirectional attention for improved speech recognitioncited by 4
  8. 2023MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognitioncited by 4
  9. 2024Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognitioncited by 3
  10. 2023Seeking Next Layer Neurons' Attention for Error-Backpropagation-Like Training in a Multi-Agent Network Frameworkcited by 2
  11. 2025Aligning Generative Speech Enhancement with Perceptual Feedbackcited by 2
  12. 2024Fairness-Aware Job Scheduling for Multi-Job Federated Learningcited by 1
  13. 2024Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbationcited by 1
  14. 2025DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learningcited by 0
  15. 2025AudioScene: Integrating Object-Event Audio into 3D Scenescited by 0
  16. 2026Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancementcited by 0
  17. 2026Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Textcited by 0
  18. 2026Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correctioncited by 0