内容紹介

Recognition of conversation scenes has recently been tackled to achieve a variety of tasks such as automatic annotation, minute taking, and meeting assistance. Since participants speak spontaneously in a conversation, a recorded conversation includes many speaker overlaps and ambient noise. To handle such complicated recordings, speech signal processing techniques play an important role. In this lecture, I will focus on some multi-channel speech enhancement and "who spoke when" estimation (speaker diarization) techniques for conversation scene analysis. Prototype meeting recognition and meeting assistance systems are also introduced.

詳細情報

刊年

2012

形態

電子化映像資料(1時間29分53秒)

別書名

Speech processing techniques for conversation scene analysis

シリーズ名

情報科学研究科・ゼミナール講演 ; 平成24年度

注記

講演者所属: 日本電信電話株式会社 NTTコミュニケーション科学基礎研究所

講演日: 平成24年7月9日

講演場所: 情報科学研究科大講義室L1

標題言語

日本語 (jpn)

本文言語

日本語 (jpn)

著者情報

荒木, 章子 (アラキ, ショウコ)