A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Eigentriphones for Context-Dependent Acoustic Modeling
2013
IEEE Transactions on Audio, Speech, and Language Processing
Most automatic speech recognizers employ tied-state triphone hidden Markov models (HMM), in which the corresponding triphone states of the same base phone are tied. State tying is commonly performed with the use of a phonetic regression class tree which renders robust context-dependent modeling possible by carefully balancing the amount of training data with the degree of tying. However, tying inevitably introduces quantization error: triphones tied to the same state are not distinguishable in
doi:10.1109/tasl.2013.2248722
fatcat:umyhdvopcrfc3ivfp7yrega54e