·ビジネス·
B2

Google's New AI Tool Cleans Up Transcripts by Removing Filler Words

Googleの新しいAIツール、フィラーの削除により文字起こしを清書

#Google#Artificial Intelligence#Transcription#Speech Recognition
0:00 / 0:00

Imagine recording a speech or interview without having to worry about speech hesitations showing up in your notes. Google has introduced Gemini 3.5 Transcribe, an artificial intelligence model designed to make voice transcriptions cleaner and more professional by automatically filtering out filler words like "um" and "uh."

without having to V= 〜する必要なくdesigned to V= 〜する目的で設計された

The new model represents a major advancement over Google's previous transcription tool, Chirp 3, particularly in multilingual performance and reducing wording error rates. In addition to stripping away unwanted verbal slips, Gemini 3.5 Transcribe automatically formats spoken text into readable paragraphs. It supports more than 85 languages and can identify up to three distinct speakers in pre-recorded audio, complete with word-level timestamps.

In addition to V-ing= 〜に加えて

To prevent crucial terminology from being altered, the system allows users to upload custom vocabularies. This means specialized industry jargon, technical terms, and unique names are accurately transcribed without requiring tedious manual corrections afterward.

prevent ... from being V-ed= …が〜されるのを防ぐ

The feature is initially rolling out in English for macOS users on the Gemini app and on Android through the Rambler dictation feature in select regions. Developers can also access the tool in public preview via the Gemini API, Google AI Studio, and Antigravity, with web support for Chrome coming soon.

roll out= (新機能・製品などを)順次公開・展開する

学習ノート

表現パターン

パターン意味
without having to V〜する必要なく
designed to V〜する目的で設計された
In addition to V-ing〜に加えて
prevent ... from being V-ed…が〜されるのを防ぐ
roll out(新機能・製品などを)順次公開・展開する

語彙

レベル意味
filler wordsB1フィラー(「えーと」や「あのー」などの言いよどみ)
multilingualB2多言語の、複数の言語を扱う
verbal slipsB2言い間違い、言いよどみ
timestampsB2タイムスタンプ(発言箇所の時刻記録)
tediousB2退屈な、長くて面倒な
jargonC1専門用語、業界用語

言語メモ

  • 英語の話し言葉における「um」や「uh」のようなフィラー(言いよどみ)は会話では自然ですが、文字起こしテキストでは冗長になるため、LLMを用いた自動除去技術が注目されています。
  • 従来の文字起こし(ASR)では専門用語の誤認識が課題でしたが、カスタム語彙のアップロード機能により、業界用語や固有名詞の精度が大幅に向上しています。

練習

読んだ内容を確認しましょう。

  1. This means specialized industry  , technical terms, and unique names are accurately transcribed without requiring tedious manual corrections afterward.

  2. What is one key capability of Gemini 3.5 Transcribe mentioned in the article?

  3. What does the pattern "without having to V" mean in this context?

Source: The Verge