MétaCan
Menu
Back to cohort

MMT-Net: A Lightweight Hybrid of Multi-Scale Modern TCN and Transformer for Real-Time SELD

2025· article· W7117452909 on OpenAlexfundno aff
Dohyun Kim, Jehyun Park, Donghan Kim

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicMusic and Audio Processing
Canadian institutionsnot available
FundersNational Research FoundationMinistry of Trade, Industry and EnergyIndian Institute of Technology, PatnaKorea Institute of Planning and Evaluation for Technology in Food, Agriculture and ForestryRural Development AdministrationMinistry of Science and ICT, South KoreaMinistry of Agriculture - Saskatchewan
KeywordsTransformerInferenceRobotAmbisonicsConvolutional neural networkEvent (particle physics)Capacitive sensing

Abstract

fetched live from OpenAlex

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$\approx 7 \times$(to$\sim 2 \mathrm{M}$) and achieves$\approx 3 \times$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 machine prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.005
Threshold uncertainty score0.010

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0030.001

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.

Opus teacher head0.014
GPT teacher head0.256
Teacher spread0.242 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicMusic and Audio ProcessingFrench-language works237,207