Code-Switching speech recognition for closely related languages
نویسندگان
چکیده
This work presents an approach to recognition of multispeaker conversational speech with code-switching between Ukrainian and Russian languages. Both inter-sentential and intra-sentential code-switching is handled. The approach takes into account peculiarities of phonetic systems of the closely related Russian and Ukrainian languages. A crosslingual LVCSR system is developed. The acoustic model and pronunciation lexicon are based on Ukrainian phone set. Modeling of pronunciation variation in lexicons helps to cope not only with code-switching speech but also with accented speech. Results of code-switching speech recognition are presented. The approach is suitable especially in cases of intra-sentential code-switching where language identification is problematic. Index Terms mixed speech, bilingual speech, codeswitching, Ukrainian, Russian
منابع مشابه
Language Identification by Using Syllable-Based Duration Classification on Code-Switching Speech
Many approaches to automatic spoken language identification (LID) on monolingual speech are successfully, but LID on the code-switching speech identifying at least 2 languages from one acoustic utterance challenges these approaches. In [6], we have successfully used one-pass approach to recognize the Chinese character on the Mandarin-Taiwanese code-switching speech. In this paper, we introduce ...
متن کاملLanguage identification of code Switching sentences and multilingual sentences of under-resourced languages by using multi structural word information
Language identification (LID) is a process to identify the languages used in a text or speech. Code switching is the switching of a language in a sentence or speech utterance. This paper focuses on LID of words in code switching sentences. Code switching can occur intersentential or intrasentential. The reasons why a writer switches from one language to another due to various reasons and among ...
متن کاملAddressing Code-Switching in French/Algerian Arabic Speech
This study focuses on code-switching (CS) in French/Algerian Arabic bilingual communities and investigates how speech technologies, such as automatic data partitioning, language identification and automatic speech recognition (ASR) can serve to analyze and classify this type of bilingual speech. A preliminary study carried out using a corpus of Maghrebian broadcast data revealed a relatively hi...
متن کاملSpeech Recognition on English-Mandarin Code-Switching Data using Factored Language Models - with Part-of-Speech Tags, Language ID and Code-Switch Point Probability as Factors pdfsubject=Multilingual Speech Recognition
Code-switching is defined as ”the alternate use of two or more languages in the same utterance or conversation” [1]. CS is a wide-spread phenomenon in multilingual communities, where multiple languages are concurrently used in a conversation. For automatic speech recognition (ASR), particularly intra-sentential code-switching poses an interesting challenge due to the multilingual context for la...
متن کاملAn Investigation of Code-Switching Attitude Dependent Language Modeling
In this paper, we investigate the adaptation of language modeling for conversational Mandarin-English Code-Switching (CS) speech and its effect on speech recognition performance. First, we investigate the prediction of code switches based on textual features with focus on Partof-Speech (POS) tags. We show that the switching attitude is speaker dependent and utilize this finding to cluster the t...
متن کامل