Intelligent Transcription System Based on Spontaneous Speech Processing

• Published in: Second International Conference on Informatics Research for Development of Knowledge Society Infrastructure (ICKS'07) pp. 19 - 26
• Main Author: Kawahara, T.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2007
• Subjects: Acoustic signal detection; Automatic speech recognition; Cleaning; Humans; Intelligent systems; Oral communication; Probability; Speech processing; Speech recognition; Surface-mount technology
• DOI: 10.1109/ICKS.2007.13
• ISBN: 9780769528113; 0769528112

With the improvement of the speech recognition technology, semi-automatic generation of transcripts or document records of lectures and meetings has become one of its promising applications. For this purpose, we need to take into account post-processing that includes cleaning of verbatim transcripts and segmentation into sentence and paragraph units. This article presents a novel statistical framework for an intelligent transcription system. The recent progress of automatic speech recognition of lectures and meetings is also reported. Then, several approaches to sentence unit detection and disfluency detection are described, as they are significant in the post-processing of transcripts generated by the speech recognizer