A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Advances in Subword-based HMM-DNN Speech Recognition Across Languages
2020
Computer Speech and Language
A B S T R A C T We describe a novel way to implement subword language models in speech recognition systems based on weighted finite state transducers, hidden Markov models, and deep neural networks. The acoustic models are built on graphemes in a way that no pronunciation dictionaries are needed, and they can be used together with any type of subword language model, including character models. The advantages of short subword units are good lexical coverage, reduced data sparsity, and avoiding
doi:10.1016/j.csl.2020.101158
fatcat:xs2lq7o4cbgfdbry5nxqlsz7ra