arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.06253cs.LGcs.AI
收藏

基于CTC的缅甸语语音识别端到端技术研究

Exploring CTC Based End-to-End Techniques for Myanmar Speech Recognition

University of Information Technology(信息技术大学)

Khin Me Me Chit, Laet Laet Lin

摘要:

在这项工作中,我们探索了一个基于连接时间分类(CTC)的端到端自动语音识别(ASR)模型的缅甸语。对模型的拓扑结构进行了一系列实验,其中增加和删除卷积层,使用不同深度的双向长短期记忆(BLSTM)层,并研究了不同的标签编码方法。实验是在低资源的情况下进行的,使用我们录制的近26小时的缅甸语音语料库。最佳模型在测试集上实现了4.72%的字符出错率(CER)和12.38%的音节出错率(SER)。

英文摘要:

In this work, we explore a Connectionist Temporal Classification (CTC) based end-to-end Automatic Speech Recognition (ASR) model for the Myanmar language. A series of experiments is presented on the topology of the model in which the convolutional layers are added and dropped, different depths of bidirectional long short-term memory (BLSTM) layers are used and different label encoding methods are investigated. The experiments are carried out in low-resource scenarios using our recorded Myanmar speech corpus of nearly 26 hours. The best model achieves character error rate (CER) of 4.72% and syllable error rate (SER) of 12.38% on the test set.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑