How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines2018
- Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline2018
- An analysis of environment, microphone and data simulation mismatches in robust speech recognitionComputer Speech & Language, 2017
- Improved MVDR Beamforming Using Single-Channel Mask Prediction Networks2016
- Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI2016
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Elimination of the musical noise phenomenon with the Ephraim and Malah noise suppressorIEEE Transactions on Speech and Audio Processing, 1994
- Image method for efficiently simulating small-room acousticsThe Journal of the Acoustical Society of America, 1979
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979