HMM-separation-based speech recognition for a distant moving speaker.

This paper presents a hands-free speech recognition method based on HMM composition and separation for speech contaminated not only by additive noise but also by an acoustic transfer function. The method realizes an improved user interface such that a user is not encumbered by microphone equipment i...

Celý popis

Podrobná bibliografie
Vydáno v:	IEEE Transactions on speech and audio processing 9, 2 (2001).
Hlavní autor:	Takiguchi, T.
Médium:	Článek
Jazyk:	English
Témata:	HMM parameter estimation. HMM speech composition. HMM speech separation. HMM-separation-based speech recognition. MLE. Acoustic transfer function. Additive noise. Convolutional acoustic distortion. Distant moving speaker. Hands-free speech recognition. Maximum likelihood estimation. Noisy environment. Performance. Real distant-talking speech. Reverberant room. Sound source. User interface.