A factorial HMM aproach to robust isolated digit recognition in background music
M Hasegawa-Johnson, A Deoras - Proc. Interspeech 2004, 2004 - isca-archive.org
M Hasegawa-Johnson, A Deoras
Proc. Interspeech 2004, 2004•isca-archive.orgThis paper presents a novel solution to the problem of isolated digit recognition in
background music. A Factorial Hidden Markov Model (FHMM) architecture is proposed to
accurately model the simultaneous occurrence of two independent processes, such as an
utterance of a digit and an excerpt of music. The FHMM is implemented with its equivalent
HMM by extending Nadas' MIXMAX algorithm to a mixture of Gaussians PDF. At around 0
dB SNR, the proposed system shows an average relative reduction in word error rate of 57 …
background music. A Factorial Hidden Markov Model (FHMM) architecture is proposed to
accurately model the simultaneous occurrence of two independent processes, such as an
utterance of a digit and an excerpt of music. The FHMM is implemented with its equivalent
HMM by extending Nadas' MIXMAX algorithm to a mixture of Gaussians PDF. At around 0
dB SNR, the proposed system shows an average relative reduction in word error rate of 57 …
This paper presents a novel solution to the problem of isolated digit recognition in background music. A Factorial Hidden Markov Model (FHMM) architecture is proposed to accurately model the simultaneous occurrence of two independent processes, such as an utterance of a digit and an excerpt of music. The FHMM is implemented with its equivalent HMM by extending Nadas' MIXMAX algorithm to a mixture of Gaussians PDF. At around 0 dB SNR, the proposed system shows an average relative reduction in word error rate of 57% in the recognition of isolated digits in background music.
isca-archive.org