Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Pricing
Podcast Image

耳でテクノロジーニュース

音声認識の革命 Conformer-1

12 Apr 2025

Description

最新の音声認識モデル「Conformer-1」の紹介。570,000時間の音声データを使い、「Noisy Student Training」という手法で単語誤認識率を大幅に改善。背景ノイズにも強くなり、日常の音声認識技術がさらに便利になる可能性を解説。論文元:http://arxiv.org/abs/2404.07341v2

Audio
Featured in this Episode

No persons identified in this episode.

Transcription

This episode hasn't been transcribed yet

Help us prioritize this episode for transcription by upvoting it.

0 upvotes
🗳️ Sign in to Upvote

Popular episodes get transcribed faster

Comments

There are no comments yet.

Please log in to write the first comment.