mlsanityData to 13 Oct 2026

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

arXiv 2110.05267 ↗First posted 11 Oct 2021eess.AS cs.LG cs.SDcited by 17

Not on the map. Why?

Abstract (arXiv)

Speech enhancement (SE) aims to suppress the additive noise from a noisy speech signal to improve the speech's perceptual quality and intelligibility. However, the over-suppression phenomenon in the enhanced speech might degrade the performance of downstream automatic speech recognition (ASR) task due to the missing latent information. To alleviate such problem, we propose an interactive feature fusion network (IFF-Net) for noise-robust speech recognition to learn complementary information from the enhanced feature and original noisy feature. Experimental results show that the proposed method achieves absolute word error rate (WER) reduction of 4.1% over the best baseline on RATS Channel-A corpus. Our further analysis indicates that the proposed IFF-Net can complement some missing information in the over-suppressed enhanced feature.

Key facts. Cited by 17 papers in the map (data through 13 Oct 2026). Builds on 13 of its 28 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

13 of 28 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,106
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,991
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,601
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,979
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,844
  7. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
  8. 2020TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aidscited by 42
  9. 2019Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modelingcited by 21
  10. 2020Interactive Speech and Noise Modeling for Speech Enhancementcited by 12
  11. 2021Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speechcited by 10
  12. 2020Dual Application of Speech Enhancement for Automatic Speech Recognitioncited by 8
1 more
  1. 2020Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognitioncited by 7

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 0; 2025: 1; 2026: 2.

17 papers.

Sort:

By area:

  1. 2022Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learningcited by 21
  2. 2023Metric-oriented Speech Enhancement using Diffusion Probabilistic Modelcited by 11
  3. 2022Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognitioncited by 10
  4. 2023Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separationcited by 10
  5. 2023Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognitioncited by 10
  6. 2023Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASRcited by 10
  7. 2023Unsupervised Noise adaptation using Data Simulationcited by 9
  8. 2023Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognitioncited by 9
  9. 2023Noise-aware Speech Enhancement using Diffusion Probabilistic Modelcited by 9
  10. 2023Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognitioncited by 7
  11. 2022Speech-text based multi-modal training with bidirectional attention for improved speech recognitioncited by 4
  12. 2023MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognitioncited by 4
5 more
  1. 2023ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learningcited by 2
  2. 2025A 71.2-μW Speech Recognition Accelerator with Recurrent Spiking Neural Networkcited by 1
  3. 2023On the Efficacy and Noise-Robustness of Jointly Learned Speech Emotion and Automatic Speech Recognitioncited by 0
  4. 2026Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognitioncited by 0
  5. 2026Training-Free Intelligibility-Guided Observation Addition for Noisy ASRcited by 0