Room Acoustic Characterization with Smartphone-Based Automated Speech Recognition
Bibliographic record
Abstract
Characterizing and monitoring the acoustic quality of a room is important for maintaining effective speech communication. Noise and echoes make speech harder to perceive, especially for individuals with auditory disabilities or remote conference participants. Reverberation time and noise level are common performance measures, but these are static measures and can be difficult for non-specialists to measure and interpret. In this work we consider smartphone-based automated speech recognition (ASR) as a proxy for speech intelligibility to assess room acoustics. We evaluate the error rate of the on-device ASR transcription of recordings of real speech and noise in a reverberant conference room. We also model the spatial processing benefits of binaural hearing by comparing recordings from an omnidirectional microphone (remote participant) and a microphone array (local participant). In a quiet room with a nearby microphone the ASR systems achieve near-perfect recognition rates, and performance degrades gradually as noise level or microphone distance are increased. Array processing improves robustness, providing an effective SNR improvement of around 3 dB. The results demonstrate that smartphone-based ASR can provide a convenient and readily available real-time assessment of the effects of noise and reverberation, even when those distortions are not apparent to local listeners.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".