Matches in SemOpenAlex for { <https://semopenalex.org/work/W2108367224> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2108367224 abstract "The voice activity detection (VAD) is crucial in all kinds of speech applications. However, almost all existing VAD algorithms suffer from the nonstationarity of both speech and noise. To combat this difficulty, we propose a new voice activity detector, which is based on the Mel-energy features and an adaptive threshold related to the signal-to-noise ratio (SNR) estimates. In this paper, we first justify the robustness of the Bayes classifier using the Mel-energy features over that using the Fourier spectral features in various noise environments. Then, we design an algorithm using the dynamic Mel-energy estimator and the adaptive threshold which depends on the SNR estimates. In addition, a realignment scheme is incorporated to correct the sparse-and- spurious noise estimates. Numerous simulations are carried out to evaluate the performance of our proposed VAD method and the comparisons are made with a couple existing representative schemes, namely the VAD using the likelihood ratio test with Fourier spectral energy features and that based on the enhanced time-frequency parameters. Three types of noise, namely white noise (stationary), babble noise (nonstationary) and vehicular noise (nonstationary) were artificially added by the computer for our experiments. As a result, our proposed VAD algorithm significantly outperforms other existing methods as illustrated by the corresponding receiver operating curves (ROCs). Finally, we demonstrate one of the major applications, namely speech waveform compression, associated with our new robust VAD scheme and quantify the effectiveness in terms of compression efficiency." @default.
- W2108367224 created "2016-06-24" @default.
- W2108367224 creator A5036278398 @default.
- W2108367224 creator A5040614086 @default.
- W2108367224 date "2007-11-01" @default.
- W2108367224 modified "2023-09-26" @default.
- W2108367224 title "Speech Waveform Compression Using Robust Adaptive Voice Activity Detection for Nonstationary Noise in Multimedia Communications" @default.
- W2108367224 cites W1535749512 @default.
- W2108367224 cites W1852767984 @default.
- W2108367224 cites W1969674180 @default.
- W2108367224 cites W1974387177 @default.
- W2108367224 cites W2104132386 @default.
- W2108367224 cites W2119393553 @default.
- W2108367224 cites W2127830789 @default.
- W2108367224 cites W2129120544 @default.
- W2108367224 cites W2146064606 @default.
- W2108367224 cites W2149053750 @default.
- W2108367224 cites W2156038773 @default.
- W2108367224 cites W2165304462 @default.
- W2108367224 cites W2165630397 @default.
- W2108367224 cites W2171271801 @default.
- W2108367224 cites W2535438430 @default.
- W2108367224 cites W2799061466 @default.
- W2108367224 cites W2164542038 @default.
- W2108367224 doi "https://doi.org/10.1109/glocom.2007.586" @default.
- W2108367224 hasPublicationYear "2007" @default.
- W2108367224 type Work @default.
- W2108367224 sameAs 2108367224 @default.
- W2108367224 citedByCount "2" @default.
- W2108367224 countsByYear W21083672242015 @default.
- W2108367224 crossrefType "proceedings-article" @default.
- W2108367224 hasAuthorship W2108367224A5036278398 @default.
- W2108367224 hasAuthorship W2108367224A5040614086 @default.
- W2108367224 hasConcept C104317684 @default.
- W2108367224 hasConcept C105795698 @default.
- W2108367224 hasConcept C112633086 @default.
- W2108367224 hasConcept C115961682 @default.
- W2108367224 hasConcept C154945302 @default.
- W2108367224 hasConcept C185429906 @default.
- W2108367224 hasConcept C185592680 @default.
- W2108367224 hasConcept C186370098 @default.
- W2108367224 hasConcept C197424946 @default.
- W2108367224 hasConcept C204201278 @default.
- W2108367224 hasConcept C28490314 @default.
- W2108367224 hasConcept C33923547 @default.
- W2108367224 hasConcept C41008148 @default.
- W2108367224 hasConcept C554190296 @default.
- W2108367224 hasConcept C55493867 @default.
- W2108367224 hasConcept C61328038 @default.
- W2108367224 hasConcept C63479239 @default.
- W2108367224 hasConcept C76155785 @default.
- W2108367224 hasConcept C94915269 @default.
- W2108367224 hasConcept C99498987 @default.
- W2108367224 hasConceptScore W2108367224C104317684 @default.
- W2108367224 hasConceptScore W2108367224C105795698 @default.
- W2108367224 hasConceptScore W2108367224C112633086 @default.
- W2108367224 hasConceptScore W2108367224C115961682 @default.
- W2108367224 hasConceptScore W2108367224C154945302 @default.
- W2108367224 hasConceptScore W2108367224C185429906 @default.
- W2108367224 hasConceptScore W2108367224C185592680 @default.
- W2108367224 hasConceptScore W2108367224C186370098 @default.
- W2108367224 hasConceptScore W2108367224C197424946 @default.
- W2108367224 hasConceptScore W2108367224C204201278 @default.
- W2108367224 hasConceptScore W2108367224C28490314 @default.
- W2108367224 hasConceptScore W2108367224C33923547 @default.
- W2108367224 hasConceptScore W2108367224C41008148 @default.
- W2108367224 hasConceptScore W2108367224C554190296 @default.
- W2108367224 hasConceptScore W2108367224C55493867 @default.
- W2108367224 hasConceptScore W2108367224C61328038 @default.
- W2108367224 hasConceptScore W2108367224C63479239 @default.
- W2108367224 hasConceptScore W2108367224C76155785 @default.
- W2108367224 hasConceptScore W2108367224C94915269 @default.
- W2108367224 hasConceptScore W2108367224C99498987 @default.
- W2108367224 hasLocation W21083672241 @default.
- W2108367224 hasOpenAccess W2108367224 @default.
- W2108367224 hasPrimaryLocation W21083672241 @default.
- W2108367224 hasRelatedWork W1628467322 @default.
- W2108367224 hasRelatedWork W1962303650 @default.
- W2108367224 hasRelatedWork W2068323328 @default.
- W2108367224 hasRelatedWork W2077297627 @default.
- W2108367224 hasRelatedWork W2098265087 @default.
- W2108367224 hasRelatedWork W2106462793 @default.
- W2108367224 hasRelatedWork W2115066753 @default.
- W2108367224 hasRelatedWork W2144256180 @default.
- W2108367224 hasRelatedWork W2418631473 @default.
- W2108367224 hasRelatedWork W2485008119 @default.
- W2108367224 isParatext "false" @default.
- W2108367224 isRetracted "false" @default.
- W2108367224 magId "2108367224" @default.
- W2108367224 workType "article" @default.