Application Of Speech Rate Conversion Technology To Video Editing: Allows Up To 5 Times Normal Speed Playback While Maintaining Speech Intelligibility

Imai A, Seiyama N, Mishima T, Takagi T, Miyasaka E. Application Of Speech Rate Conversion Technology To Video Editing: Allows Up To 5 Times Normal Speed Playback While Maintaining Speech Intelligibility. In: AES Conference: 20th International Conference: Archiving, Restoration, and New Methods of Recording. Audio Engineering Society; 2001. Paper 1934. Available from: https://aes.org/publications/elibrary-page/?id=10055

@inproceedings{Imai2001_10055,
  author = {Imai, Atsushi and Seiyama, Nobumasa and Mishima, Takeshi and Takagi, Tohru and Miyasaka, Eiichi},
  title = {{Application Of Speech Rate Conversion Technology To Video Editing: Allows Up To 5 Times Normal Speed Playback While Maintaining Speech Intelligibility}},
  booktitle = {AES Conference: 20th International Conference: Archiving, Restoration, and New Methods of Recording},
  note = {Paper 1934},
  year = {2001},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=10055}
}

TY  - CPAPER
TI  - Application Of Speech Rate Conversion Technology To Video Editing: Allows Up To 5 Times Normal Speed Playback While Maintaining Speech Intelligibility
AU  - Imai, Atsushi
AU  - Seiyama, Nobumasa
AU  - Mishima, Takeshi
AU  - Takagi, Tohru
AU  - Miyasaka, Eiichi
T2  - AES Conference: 20th International Conference: Archiving, Restoration, and New Methods of Recording
M1  - Paper 1934
PY  - 2001
DA  - 2001/10/06
UR  - https://aes.org/publications/elibrary-page/?id=10055
PB  - Audio Engineering Society
LA  - en
AB  - This paper describes an application of speech rate conversion technology to video editing. In video editing, it is common to search through the material at several times normal speed. The speech rate conversion technology maintains the original pitch and timbre of speech despite playing it back at a faster rate, which is varied adaptively to permit fast listening in real-time. In listening tests, users were able to comprehend speech played at up to 5 times normal speed which was incomprehensible without the adaptive rate conversion.
ER  -