Spoken language processing for simultaneous speech understanding

2014 Fiscal Year Final Research Report

• Project/Area Number: 22300051
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Nagoya University
• Principal Investigator: MATSUBARA Shigeki 名古屋大学, 情報科学研究科, 准教授 (20303589)
• Co-Investigator(Kenkyū-buntansha): KASHIOKA Hideki 独立行政法人情報通信研究機構, 脳情報通信融合研究センター, 室長 (10395022) ; KATO Yoshihide 名古屋大学, 情報連携統括本部, 准教授 (20362220) ; OHNO Tomohiro 名古屋大学, 情報基盤センター, 助教 (20402472)
• Project Period (FY): 2010-04-01 – 2015-03-31
• Keywords: 音声言語処理 / 構文解析 / 意味解析 / 機械翻訳 / 対話処理 / 字幕生成 / 言語資源 / コーパス

Outline of Final Research Achievements

As one of language technologies for realization of real-time spoken language systems, we developed methods for incremental analysis of spoken languages. The incremental analysis means processing spoken languages and generating the analysis results synchronously with speech inputs. We defined a style of the dependency structure for incremental analysis and demonstrated the feasibility of such the analysis process. We applied the incremental analysis to spoken language systems such as real-time captioning and experimentally indicated the effectiveness of incremental language analysis.

Free Research Field

自然言語処理