Experimental Teaching System for Bone-Conducted Speech Enhancement and Edge-Deployable Speech Intelligence

Speech interfaces are becoming ubiquitous in medical and industrial devices, yet undergraduate laboratory teaching of speech signal processing still works almost exclusively on air-conducted recordings and supervised pipelines, ignoring both the physiology of alternative sensing channels and the data scarcity that dominates real deployments. This paper reports the design of an experimental teaching system that converts an active bone-conducted speech research programme, centred on a pre-trained Transformer with low-rank driven sparsity bootstrapping (TransLRC), into a four-tier undergraduate laboratory curriculum with an engineering layer. Four principles govern the design: constructive alignment, experiential progression, the research-teaching nexus, and the CDIO lifecycle. Each tier is anchored to a bottleneck that is genuinely open in the source research: characterising the body-channel distortion of bone-conducted speech, pre-training spectral representations without paired data, pruning attention through low-rank structure, and evaluating generalisation to unseen speakers under real-time budgets. Thirty-two laboratory units (64 contact hours) are organised into six modules with staged delivery and criterion-referenced assessment that admits documented negative results, mirroring the source study’s finding that pre-training and low-rank constraints contribute separable, measurable gains. Because the source protocol runs end-to-end on a single consumer GPU with a low-cost bone-conduction sensor, the curriculum targets faithful reproduction rather than scale-reduced approximation, giving students an unusually direct path from published result to reproduced result.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-16
DOI
https://doi.org/10.20944/preprints202611.1579.v1
Primary Topic
Experimental Learning in Engineering
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Experimental Teaching System for Bone-Conducted Speech Enhancement and Edge-Deployable Speech Intelligence

Lu Huang, Jin Li
Preprints.org
Experimental Learning in Engineering
preprint

Experimental Teaching System for Bone-Conducted Speech Enhancement and Edge-Deployable Speech Intelligence

Lu Huang, Jin Li
preprint en

Abstract

Speech interfaces are becoming ubiquitous in medical and industrial devices, yet undergraduate laboratory teaching of speech signal processing still works almost exclusively on air-conducted recordings and supervised pipelines, ignoring both the physiology of alternative sensing channels and the data scarcity that dominates real deployments. This paper reports the design of an experimental teaching system that converts an active bone-conducted speech research programme, centred on a pre-trained Transformer with low-rank driven sparsity bootstrapping (TransLRC), into a four-tier undergraduate laboratory curriculum with an engineering layer. Four principles govern the design: constructive alignment, experiential progression, the research-teaching nexus, and the CDIO lifecycle. Each tier is anchored to a bottleneck that is genuinely open in the source research: characterising the body-channel distortion of bone-conducted speech, pre-training spectral representations without paired data, pruning attention through low-rank structure, and evaluating generalisation to unseen speakers under real-time budgets. Thirty-two laboratory units (64 contact hours) are organised into six modules with staged delivery and criterion-referenced assessment that admits documented negative results, mirroring the source study’s finding that pre-training and low-rank constraints contribute separable, measurable gains. Because the source protocol runs end-to-end on a single consumer GPU with a low-cost bone-conduction sensor, the curriculum targets faithful reproduction rather than scale-reduced approximation, giving students an unusually direct path from published result to reproduced result.

Preprints.org
Experimental Learning in Engineering
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon