dohyeon

  • 홈
  • 태그
  • 방명록
DOHYEON

LITEASR 1

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

Referenceshttps://arxiv.org/abs/2502.20583 LiteASR: Efficient Automatic Speech Recognition with Low-Rank ApproximationModern automatic speech recognition (ASR) models, such as OpenAI's Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce LiteASR, a low-rarxiv.org Introduction현 ..

[Efficient AI]/[Efficient AI] Tensor Decomposition 2026.08.04
이전
1
다음
더보기
프로필사진

dohyeon

M.S. Student @ GIST AI

  • 분류 전체보기 (12) N
    • [Audio Papers] (6)
      • [Audio & Speech Fundamental.. (5)
      • [Automatic Speech Recogniti.. (0)
      • [Keyword Spotting] (0)
    • [Efficient AI] (4) N
      • [Efficient AI] Quantization (0)
      • [Efficient AI] Knowledge Di.. (3)
      • [Efficient AI] Tensor Decom.. (1) N
    • [Fundamentals] (1)
      • [Fundamentals] 논문 (1)
    • [Model Architecture] (0)
    • [기타] (1)
      • XAI (1)

Tag

Efficient AI, VkD, psds, 경량화, Knowledge Distillation, Whisper 경량화, 멜스펙트로그램, mean teacher, 텐서분해, dcase, psd-roc, mel-spectrogram, Distill-Whisper, STT 경량화, mel spectrogram, 텐서 분해, LITEASR, 모델 경량화, 지식증류, polyphonic sed,

최근글과 인기글

  • 최근글
  • 인기글

최근댓글

공지사항

Github Linkedin

Copyright © Daum Corp. All rights reserved.

티스토리툴바