· 2017
A study on data augmentation of reverberant speech for robust speech recognition
- 922citations
- 2017year
Short summary
Simulating room impulse responses (RIRs) and adding point-source noises to reverberant speech data eliminates the performance gap between simulated and real RIRs for far-field ASR, and even improves close-talking ASR.
AI-generated from the title and abstract; the full text is not read.
Key points
- Simulated room impulse responses (RIRs) combined with point-source noises match real RIR performance for far-field ASR.
- The proposed data augmentation method improves ASR performance in both distant-talking and close-talking scenarios.
- This approach addresses the cost of collecting real multi-condition training data by using simulation.
- Evaluation was conducted on multiple LVCSR tasks representing both scenarios.
AI-generated from the title and abstract; the full text is not read.
Abstract
The environmental robustness of DNN-based acoustic models can be significantly improved by using multi-condition training data. However, as data collection is a costly proposition, simulation of the desired conditions is a frequently adopted strategy. In this paper we detail a data augmentation approach for far-field ASR. We examine the impact of using simulated room impulse responses (RIRs), as real RIRs can be difficult to acquire, and also the effect of adding point-source noises. We find that the performance gap between using simulated and real RIRs can be eliminated when point-source noises are added. Further we show that the trained acoustic models not only perform well in the distant-talking scenario but also provide better results in the close-talking scenario. We evaluate our approach on several LVCSR tasks which can adequately represent both scenarios.
The authors' abstract, as published at the source., 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science