MMT-Net: A Lightweight Hybrid of Multi-Scale Modern TCN and Transformer for Real-Time SELD
Bibliographic record
Abstract
Existing autonomous robots rely on LiDAR and cameras to perceive their surroundings, but they remain vulnerable to occluded threats such as obstacles behind corners. Therefore, auditory perception is essential for safe operation in complex environments. Prior sound event localization and detection (SELD) approaches have employed FirstOrder Ambisonics with four microphones (FOA) with Transformer or RNN-based models. However, these architectures require large parameter counts and incur high latency, making them unsuitable for real-time operation. In this paper, we propose MMT-Net, a lightweight SELD model that uses only two microphones and integrates a Transformer-based front-end with a Multi-scale Modern Temporal Convolutional Network (MM-TCN) back-end. Compared to Conformerbased models, MMT-Net reduces the parameters count by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\approx 7 \times$</tex> (to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\sim 2 \mathrm{M}$</tex>) and achieves <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\approx 3 \times$</tex> faster inference speed with only a 1 % drop in F1-score. Furthermore, on NVIDIA Jetson Xavier NX/Orin AGX, MMT-Net runs at over 20 fps, demonstrating real-time capability on embedded platforms.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".