Upper and lower bounds on the mean of noisy speech application to minimax classification.

Upper and lower bounds on the mean of noisy speech application to minimax classification.

In this paper, we derive upper and lower bounds on the mean of speech corrupted by additive noise. The bounds are derived in the log spectral domain. Also approximate bounds on the first and second order time derivatives are developed. It is also shown how to transform these bounds to the mel freque...

Deskribapen osoa

Xehetasun bibliografikoak
Argitaratua izan da:IEEE Transactions on speech and audio processing 10, 2 (2002).
Egile nagusia: Afify, M.
Formatua: Artikulua
Hizkuntza:English
Gaiak:
MFCQ domain.
Additive noise.
Compensation scenarios.
Log spectral domain.
Lower bounds.
Mel frequency cepstral coefficient domain.
Minimax classification.
Mismatch neighborhood.
Moving car environment.
Noisy speech.
Parametric neighborhood.
Real-life mismatch scenario.
Time derivatives.
Upper bounds.