How to Make Neural Language Models Practical for Speech Recognition

テクノロジーカテゴリーの変更を依頼記事元:

www.amazon.science

2 usersがブックマークコメント

記事へのコメント1件

注目コメント
新着コメント

rx7 "In tests comparing our neural model to a conventional model, we found that it reduced the word recognition error rate by 6.2%."

2020/10/19 リンク

rx7 "In tests comparing our neural model to a conventional model, we found that it reduced the word recognition error rate by 6.2%."

2020/10/19 リンク

注目コメント算出アルゴリズムの一部にLINEヤフー株式会社の「建設的コメント順位付けモデルAPI」を使用しています

規約違反を報告

いまの話題をアプリでチェック！

バナー広告なし
ミュート機能あり
ダークモード搭載

アプリをダウンロード

How to Make Neural Language Models Practical for Speech Recognition

An automatic-speech-recognition system — such as Alexa’s — converts speech into text, and one of ... An automatic-speech-recognition system — such as Alexa’s — converts speech into text, and one of its key components is its language model. Given a sequence of words, the language model computes the probability that any given word is the next one. For instance, a language model would predict that a sentence that begins “Toni Morrison won the Nobel” is more likely to conclude “Prize” than “dries”. L