FRILL

2000년 도입 · 논문 1편에서 사용

FRILL is a non-semantic speech embedding model trained via knowledge distillation that is fast enough to be run in real-time on a mobile device. The fastest model runs at 0.9 ms, which is 300x faster than TRILL and 25x faster than TRILL-distilled.

출처: FRILL: A Non-Semantic Speech Embedding for Mobile Devices

소개 논문: FRILL: A Non-Semantic Speech Embedding for Mobile Devices