Noise Robust End-Point Detection Algorithm Using Human Auditory and Pronunciation Characteristics

Jeong JH, Kwon MS, Lee S, Lee YW, Mori H, Cho N, Lee JW. Noise Robust End-Point Detection Algorithm Using Human Auditory and Pronunciation Characteristics. In: AES Convention 139. Audio Engineering Society; 2015. Paper 233. Available from: https://aes.org/publications/elibrary-page/?id=17909

@inproceedings{Jeong2015_17909,
  author = {Jeong, Jae-hoon and Kwon, Min Seok and Lee, Seungyeol and Lee, Young Woo and Mori, Haruyuki and Cho, Namgook and Lee, Jae Won},
  title = {{Noise Robust End-Point Detection Algorithm Using Human Auditory and Pronunciation Characteristics}},
  booktitle = {AES Convention 139},
  note = {Paper 233},
  year = {2015},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17909}
}

TY  - CPAPER
TI  - Noise Robust End-Point Detection Algorithm Using Human Auditory and Pronunciation Characteristics
AU  - Jeong, Jae-hoon
AU  - Kwon, Min Seok
AU  - Lee, Seungyeol
AU  - Lee, Young Woo
AU  - Mori, Haruyuki
AU  - Cho, Namgook
AU  - Lee, Jae Won
T2  - AES Convention 139
M1  - Paper 233
PY  - 2015
DA  - 2015/10/06
UR  - https://aes.org/publications/elibrary-page/?id=17909
PB  - Audio Engineering Society
LA  - en
AB  - A noise robust end point detection algorithm is proposed that could be used in real environment speech recognition. Inaccurate end point detection brings not only speech recognition performance reduction but also users’ tiredness. EPD algorithms based on energy level change or speech presence probability are vulnerable to high energy noises. After reducing much noise by auditory filter, one of human speech pronunciation characteristic, syllabic rate is used for checking if there is still speech component or not. The proposed algorithm shows much better performance in real environments like TV sound noise, café noise, etc.
ER  -