R
Ram Swaminathan
Researcher at Shanghai University
Publications - 7
Citations - 32
Ram Swaminathan is an academic researcher from Shanghai University. The author has contributed to research in topics: Speech coding & Audio signal processing. The author has an hindex of 3, co-authored 7 publications receiving 29 citations.
Papers
More filters
Proceedings ArticleDOI
An audio fingerprinting system based on spectral energy structure
TL;DR: Preliminary experimental results suggest that this reliable audio fingerprinting system, which extracts audio fingerprints from an audio signal based on its spectral energy structure, can work well in the application of broadcast monitoring.
Proceedings ArticleDOI
An improved spectral subtraction method
TL;DR: Voice Activity Detection is used to detect the starting and ending of the audio, so silent segment is used, and spectral decay factor is introduced to estimate noise spectrum exactly and segment SNR is used as a evaluation of de-noising effect.
Proceedings ArticleDOI
Robust audio fingerprint extraction algorithm based on 2-D chroma
TL;DR: An improved audio fingerprinting extraction algorithm which was proposed by Shazam company is proposed, which uses a combinatorial hashed time-frequency analysis of the audio, yielding unusual properties in which multiple tracks mixed together may each be identified.
Proceedings ArticleDOI
Audio fingerprint based on Spectral Flux for audio retrieval
TL;DR: This paper designs fingerprints addressing the above issues by extracting the audio fingerprints from the Spectral Flux of the clipped signal by using the AF as the feature of the algorithm, and retrieval the audio clips from the database which has store some fingerprints computed previously.
Proceedings ArticleDOI
Noise reduction based on Nearest Neighbor Estimation for audio feature extraction
TL;DR: Nearest Neighbor Estimation (NNE) is used to reduce the interference of the noise in audio fingerprinting, where audio feature points are extracted from audio clips and the impact of noise on the feature points is reduced.