Fact · Dictation
The 2017 paper says distant speech recognition still lacks robustness when non-stationary noise and acoustic reverberation are present.
Checked against its source on October 16, 2026
In the source's own words
“especially when adverse acoustic conditions originated by non-stationary noises and acoustic reverberation are met”
Realistic multi-microphone data simulation for distant speech recognition, arXiv preprint, 2017, Introduction.
Open the original- What it measures
- The sentence follows the authors' list of recent advances in spatial filtering, source separation and acoustic modeling.
- What it does not show
- A general statement from the introduction. The paper's own experiments are on simulated and recorded distant speech, not on dictation apps.