End-to-End Code Switching Language Models for Automatic Speech Recognition

2020/06/16 by M R Ahan, R., Ahan M., Shreyas Sunil Kulkarni +1
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Natural Language Processing Techniques #Sound (cs.SD) #Speech Recognition and Synthesis #Topic Modeling #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2006.08870

openalex publication_date 2020/06/16 · openalex created_date 2020/06/19 · openalex updated_date 2026/07/28

Abstract

In this paper, we particularly work on the code-switched text, one of the most common occurrences in the bilingual communities across the world. Due to the discrepancies in the extraction of code-switched text from an Automated Speech Recognition(ASR) module, and thereby extracting the monolingual text from the code-switched text, we propose an approach for extracting monolingual text using Deep Bi-directional Language Models(LM) such as BERT and other Machine Translation models, and also explore different ways of extracting code-switched text from the ASR model. We also explain the robustness of the model by comparing the results of Perplexity and other different metrics like WER, to the standard bi-lingual text output without any external information.

Citations

• Sequence Transduction with Recurrent Neural Networks
• Deep Recurrent Generative Decoder for Abstractive Text Summarization

Related

• Dual Language Models for Code Switched Speech Recognition
• Language Modeling for Code-Switching: Evaluation, Integration of\n Monolingual Data, and Discriminative Training
• Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition
• Code-Switching Detection with Data-Augmented Acoustic and Language Models
• Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives