A Novel Automatic Noise Removal Technique for Audio and Speech Signals

E.V. H, Sinha D, Saeed S, Ferreira A. A Novel Automatic Noise Removal Technique for Audio and Speech Signals. In: AES Convention 123. Audio Engineering Society; 2007. Paper 7170. Available from: https://aes.org/publications/elibrary-page/?id=14228

@inproceedings{EV2007_14228,
  author = {E.V., Harinarayanan and Sinha, Deepen and Saeed, Shamail and Ferreira, Anibal},
  title = {{A Novel Automatic Noise Removal Technique for Audio and Speech Signals}},
  booktitle = {AES Convention 123},
  note = {Paper 7170},
  year = {2007},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14228}
}

TY  - CPAPER
TI  - A Novel Automatic Noise Removal Technique for Audio and Speech Signals
AU  - E.V., Harinarayanan
AU  - Sinha, Deepen
AU  - Saeed, Shamail
AU  - Ferreira, Anibal
T2  - AES Convention 123
M1  - Paper 7170
PY  - 2007
DA  - 2007/10/06
UR  - https://aes.org/publications/elibrary-page/?id=14228
PB  - Audio Engineering Society
LA  - en
AB  - This paper introduces new ideas on wideband stationary/non-stationary noise removal for audio signals. Current noise reduction techniques have generally proven to be effective, yet these typically exhibit certain undesirable characteristics. Distortion and/or alteration of the audio characteristics of primary audio sound is a common problem. Also user intervention in identifying the noise profile is sometimes necessary. The proposed technique is centered on the classical Kalman filtering technique for noise removal but uses a novel architecture whereby advanced signal processing techniques are used to identify and preserve the richness of the audio spectrum. The paper also includes conceptual and derivative results on parameter estimation, a description of multi parameter Signal Activity Detector (SAD) and our new found improved results.
ER  -