Dual Language Models for Code Switched Speech Recognition
This addresses the problem of accurate speech recognition for bilingual speakers who code-switch, though it is incremental as it builds on existing language modeling techniques.
The paper tackled language modeling for bilingual code-switched text by proposing dual language models, which combine monolingual models with a probabilistic switching mechanism, resulting in significant improvements in perplexity and speech recognition error rates on a Mandarin-English corpus.
In this work, we present a simple and elegant approach to language modeling for bilingual code-switched text. Since code-switching is a blend of two or more different languages, a standard bilingual language model can be improved upon by using structures of the monolingual language models. We propose a novel technique called dual language models, which involves building two complementary monolingual language models and combining them using a probabilistic model for switching between the two. We evaluate the efficacy of our approach using a conversational Mandarin-English speech corpus. We prove the robustness of our model by showing significant improvements in perplexity measures over the standard bilingual language model without the use of any external information. Similar consistent improvements are also reflected in automatic speech recognition error rates.