mlsanityData to 7 Oct 2026

How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR

arXiv 2201.06685 ↗First posted 18 Jan 2022eess.AS cs.SDcited by 27

Not on the map. Why?

Abstract (arXiv)

It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with single-channel speech enhancement (SE). In this paper, we investigate the causes of ASR performance degradation by decomposing the SE errors using orthogonal projection-based decomposition (OPD). OPD decomposes the SE errors into noise and artifact components. The artifact component is defined as the SE error signal that cannot be represented as a linear combination of speech and noise sources. We propose manually scaling the error components to analyze their impact on ASR. We experimentally identify the artifact component as the main cause of performance degradation, and we find that mitigating the artifact can greatly improve ASR performance. Furthermore, we demonstrate that the simple observation adding (OA) technique (i.e., adding a scaled version of the observed signal to the enhanced speech) can monotonically increase the signal-to-artifact ratio under a mild condition. Accordingly, we experimentally confirm that OA improves ASR performance for both simulated and real recordings. The findings of this paper provide a better understanding of the influence of SE errors on ASR and open the door to future research on novel approaches for designing effective single-channel SE front-ends for ASR.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jan 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 6; 2025: 10; 2026: 5.

27 papers.

Sort:

By area:

  1. 2024Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Modelscited by 26
  2. 2022End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representationcited by 17
  3. 2023Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASRcited by 10
  4. 2023TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognitioncited by 8
  5. 2024Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridgecited by 6
  6. 2025Measuring the Effect of Transcription Noise on Downstream Language Understanding Taskscited by 6
  7. 2024A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognitioncited by 5
  8. 2024Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensorscited by 5
  9. 2024An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTScited by 4
  10. 2025Adapting Automatic Speech Recognition for Accented Air Traffic Control Communicationscited by 3
  11. 2022Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Expertscited by 2
  12. 2024Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importancecited by 2
15 more
  1. 2025CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASRcited by 2
  2. 2025A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Modelcited by 2
  3. 2023Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcriptioncited by 1
  4. 2025Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancementcited by 1
  5. 2025Error Analysis in a Modular Meeting Transcription Systemcited by 1
  6. 2023Continuous Modeling of the Denoising Process for Speech Enhancement Based on Deep Learningcited by 0
  7. 2025VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identificationcited by 0
  8. 2025SEED: Speaker Embedding Enhancement Diffusion Modelcited by 0
  9. 2025Revealing the Role of Audio Channels in ASR Performance Degradationcited by 0
  10. 2025Alternating Approach-Putt Models for Multi-Stage Speech Enhancementcited by 0
  11. 2026Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognitioncited by 0
  12. 2026Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logitscited by 0
  13. 2026Training-Free Intelligibility-Guided Observation Addition for Noisy ASRcited by 0
  14. 2026Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Endscited by 0
  15. 2026Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detectioncited by 0