Lexicon-building methods for an acoustic sub-word based speech recognizer
Citations
5 citations
5 citations
Cites methods from "Lexicon-building methods for an aco..."
...These methods typically involved [20,21]: (a) segmentation of speech utterances based on an acoustic similarity measure; (b) clustering of the segments using methods such as k-means to a pre-set number of subword units/clusters; and (c) finding pronunciations for each word from the occurrences of subword units in the training data followed by another clustering step to select representative pronunciations....
[...]
3 citations
3 citations
Additional excerpts
...[8] K.K. Paliwal,1990,”Lexicon-Building Methods For An Acoustic Sub-Word Based Speech Recognizer”, CH2847-2/90/0000-0729,IEEE....
[...]
3 citations
Cites methods from "Lexicon-building methods for an aco..."
...A segmentation approach based on dynamic programming (DP) was proposed in [39], and used later in [35, 40, 41, 42, 43]....
[...]
References
21,819 citations
7,935 citations
1,637 citations
245 citations
218 citations