A Comparative Study on Selecting Acoustic Modeling Units for WFST-based Mongolian Speech Recognition
Open Access
- 13 October 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (10) , 1-20
Abstract
Traditional weighted finite-state transducer– (WFST) based Mongolian automatic speech recognition (ASR) systems use phonemes as pronunciation lexicon modeling units. However, Mongolian is an agglutinative, low-resource language, and building an ASR system based on the phoneme pronunciation lexicon remains a challenge for various reasons. First, the phoneme pronunciation lexicon manually constructed by Mongolian linguists is finite, which is usually used to build a grapheme-to-phoneme conversion (G2P) model to frequently expand new words. However, the data sparsity decreases the robustness of the G2P model and affects the performance of the final ASR system. Second, homophones and polysyllabic words are common in Mongolian, which has a certain impact on the construction of the Mongolian acoustic model. To address these problems, in this work, we first propose a grapheme-to-phoneme alignment model to obtain the mapping relationship between phonemes and subword units. Then, we construct an acoustic subword segmentation set to segment words directly instead of using the traditional G2P method to predict phoneme sequences to expand the pronunciation lexicon. Further, by analyzing the Mongolian encoding form, we also propose an acoustic subword modeling units construction method that removes control characters. Finally, we investigate various acoustic subword modeling units for pronunciation lexicon construction for the Mongolian ASR system. Experiments on a Mongolian dataset with 325 hours of training show that the pronunciation lexicon based on the acoustic subword modeling unit can effectively construct the WFST-based Mongolian ASR system. Further, removing the control characters when building the acoustic subword modeling unit can further improve the ASR system performance.Keywords
Funding Information
- China National Natural Science Foundation (62366037, 62066033)
- Research Foundation for Young Scholars of Inner Mongolia University (10000-23112101/052)
This publication has 37 references indexed in Scilit:
- Morphologically motivated word classes for very large vocabulary speech recognition of Finnish and EstonianComputer Speech & Language, 2021
- Mongolian Grapheme to Phoneme Conversion by Using Hybrid Approach2018
- Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates2018
- Automatic Speech Recognition With Very Large Conversational Finnish and Estonian VocabulariesIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Improved Subword Modeling for WFST-Based Speech Recognition2017
- Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI2016
- Mongolian Speech Recognition Based on Deep Neural Networks2015
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Unsupervised models for morpheme segmentation and morphology learningACM Transactions on Speech and Language Processing, 2007
- Automatic generation of subword units for speech recognition systemsIEEE Transactions on Speech and Audio Processing, 2002