Word/sub-word lattices decomposition and combination for speech recognition

Abstract : This paper presents the benefit of using multiple lexical units in the post-processing stage of an ASR system. Since the use of sub-word units can reduce the high out-of-vocabulary rate and improve the lack of text resources in statistical language modeling, we propose several methods to decompose, normalize and combine word and sub-word lattices generated from different ASR systems. By using a sub-word information table, every word in a lattice can be decomposed into sub-word units. These decomposed lattices can be combined into a common lattice in order to generate a confusion network. This lattices combination scheme results in an absolute syllable error rate reduction of about 1.4% over the sentence MAP baseline method for a Vietnamese ASR task. By comparing with the N-best lists combination and voting method, the proposed method works better.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01392533
Contributor : Brigitte Bigi <>
Submitted on : Friday, November 4, 2016 - 2:24:58 PM
Last modification on : Monday, July 8, 2019 - 3:10:52 PM
Long-term archiving on : Sunday, February 5, 2017 - 2:03:53 PM

File

Word_sub-word_lattices_decompo...
Files produced by the author(s)

Identifiers

Citation

Viet-Bac Le, Sopheap Seng, Laurent Besacier, Brigitte Bigi. Word/sub-word lattices decomposition and combination for speech recognition. IEEE International conference on Acoustics, Speech and Signal Processing, 2008, Las Vegas, United States. pp.4321 - 4324, ⟨10.1109/ICASSP.2008.4518611⟩. ⟨hal-01392533⟩

Share

Metrics

Record views

323

Files downloads

192