In environment with considerably long reverberation time, each frame of speech is affected by reflected energy components from the preceding frames. Therefore to adapt model parameters of a state, it becomes necessary to consider these frames, and compute their contributions to current state. However, these clean speech frames preceding to a state of HMM are not known during adaptation of the models. This paper describes a method to estimate the preceding frames for a state in HMM, by splitting the state into a number of substates. The estimated sequence of frames can then be used to find reflected energy component for the state and compensate its parameters. The effectiveness of the method was confirmed by the experimental results on an isolated-word recognition task.
Cite as: Raut, C.K., Nishimoto, T., Sagayama, S. (2005) Model adaptation by state splitting of HMM for long reverberation. Proc. Interspeech 2005, 277-280, doi: 10.21437/Interspeech.2005-157
@inproceedings{raut05_interspeech,
author={Chandra Kant Raut and Takuya Nishimoto and Shigeki Sagayama},
title={{Model adaptation by state splitting of HMM for long reverberation}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={277--280},
doi={10.21437/Interspeech.2005-157}
}