Главная | Публикации | Lezhenin I. Pitchkeywordextractor: Prosody-based automatic keyword extraction for speech content

Pitchkeywordextractor: Prosody-based automatic keyword extraction for speech content

Авторы

Lezhenin I.
2017 Federated Conference on Computer Science and Information Systems (FedCSIS). – IEEE, 2017. – С. 265-269.

Краткое описание

Keyword extraction is widely used for information indexing, compressing, summarizing, etc. Existing keyword extraction techniques apply various text-based algorithms and metrics to locate the keywords. At the same time, some types of audio and audiovisual content, e. g. lectures, talks, interviews and other speech-oriented information, allow to perform keyword search by prosodic accents made by a speaker. This paper presents PitchKeywordExtractor-A n algorithm with its software prototype for prosody-based automatic keyword extraction in speech content. It operates together with a third-party automatic speech recognition system, handles speech prosody by a pitch detection algorithm and locates the keywords using pitch contour cross-correlation with four tone units taken from D. Brazil discourse intonation model. © 2017 PTI.

Lezhenin I. et al. Pitchkeywordextractor: Prosody-based automatic keyword extraction for speech content //2017 Federated Conference on Computer Science and Information Systems (FedCSIS). – IEEE, 2017. – С. 265-269.