Mathematics & AI

Mathematics & AI

ISSN: 0000-0000 · EN

Mathematics & AI is an open-access, peer-reviewed journal at the intersection of mathematics and artificial intelligence. The journal publishes original research in mathematical foundations of AI, machine learning theory, optimization, statistical learning, neural network analysis, computational mat...
Article #1006
Issue MathAI 2026 Selected Papers Special Issue
Received 02 Apr 2026
Accepted 15 May 2026
Published 22 May 2026

Deep Learning for Educational Video Analysis: Benchmarking ASR Systems and Pipeline Optimization

E
Elena Kantonistova
MathAI 2026 Selected Papers Special Issue
Published: May 22, 2026 Accepted: May 15, 2026 Received: April 2, 2026

Abstract

We present a comparative analysis of eight managed commercial speech recognition providers (provider-side preprocessing, segmentation, and serving) for educational video transcription and enrichment, evaluated on over 700 lecture recordings (900+ hours) across disciplines. The Fireworks whisper-v3-turbo endpoint offers a favorable cost–quality–latency trade-off versus surveyed alternatives. Audio preprocessing reduces billed duration by 10–25% with negligible accuracy loss. Prompt-based “Video Vocabulary” reduces terminology errors without fine-tuning. We implement a parallel pipeline that cuts end-to-end turnaround from over 30 minutes of manual effort per recording to under two minutes, supports up to 50 concurrent jobs, and achieves roughly 22× speedup at about $0.075 per hour of content for transcription plus pedagogical enrichment (summaries, chapter topics, self-check questions) at list prices. The system is deployed in production.

Cite this article

Zuev, G.; Kantonistova, E. Deep Learning for Educational Video Analysis: Benchmarking ASR Systems and Pipeline Optimization. Mathematics & AI 2026, 1, 6. https://enigma.ist/j/mathematics-ai/1/2/6

Full Text (PDF)