A
Anatoli I. Tikhotsky
Researcher at LG Electronics
Publications - 5
Citations - 169
Anatoli I. Tikhotsky is an academic researcher from LG Electronics. The author has contributed to research in topics: Noise & Signal. The author has an hindex of 3, co-authored 5 publications receiving 169 citations.
Papers
More filters
Patent
Method of segmenting an audio stream
Mikhael A. Sall,Sergei N. Gramnitskiy,Alexandr L. Maiboroda,Redkov Victor,Anatoli I. Tikhotsky,Andrei B. Viktorov +5 more
TL;DR: In this paper, a segmentation method based on the analysis of audio signal statistical features variation is proposed. But the main objective of this method is localization of segments with stationary properties, which can be used as an input data for classification, speech/music/noise attribution and so on.
Patent
Method and system for distinguishing speech from music in a digital audio signal in real time
Mikhael A. Sall,Sergei N. Gramnitskiy,Alexandr L. Maiboroda,Redkov Victor,Anatoli I. Tikhotsky,Andrei B. Viktorov +5 more
TL;DR: In this paper, a method for distinguishing speech from music in a digital audio signal in real time for the sound segments that have been segmented from an input signal of the digital sound processing systems by means of a segmentation unit on the base of homogeneity of their properties is presented.
Patent
Method of filtering noise of source digital data
Mikhael A. Sall,Sergei N. Gramnitskiy,Alexandr L. Maiboroda,Redkov Victor,Anatoli I. Tikhotsky,Andrei B. Viktorov +5 more
TL;DR: In this article, the authors proposed a method of filtering digital audio data with short delay, which comprises the steps of: (a) buffering input source DAS data, (b) calculating digital data that are being filtered from the buffered input DAS audio data, and (c) outputting a portion of the filtered digital data.
Patent
/ Method and system for real-time music/speech discrimination in digital audio signals
Sergei N. Gramnitskiy,Alexandr L. Maiboroda,Redkov Victor,Mikhael A. Sall,Anatoli I. Tikhotsky,Andrei B. Viktorov +5 more
TL;DR: In this paper, a method and system for identifying music/voice of a digital audio signal in real-time are provided to identify music and voice in real time audio data processing, where an input signal is framed into a sequence of overlapped frames according to a window function.
Patent
Method of noise filtering of source digital data
Sergei N. Gramnitskiy,Alexandr L. Maiboroda,Redkov Victor,Mikhael A. Sall,Anatoli I. Tikhotsky,Andrei B. Viktorov +5 more
TL;DR: In this article, a method for filtering noise of primitive digital data is provided to remove noise in a signal such as audio streams broadcasted or recorded using predetermined media with relatively simple integration circuit.