ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs.
Ahmed HeaklYoussef ZaghloulMennatullah AliRania HossamWalid GomaaPublished in: CoRR (2024)
Keyphrases
- machine translation
- language identification
- arabic language
- cross language information retrieval
- broadcast news
- english text
- text to speech
- statistical machine translation
- query translation
- speech recognition
- language resources
- speaker identification
- machine translation system
- cross language retrieval
- cross language
- spoken language
- target language
- source language
- bilingual dictionaries
- finite state transducers
- parallel corpora
- speech corpus
- cross language ir
- comparable corpora
- isolated word
- chinese english
- english chinese
- language learning
- pronominal anaphora
- automatic speech recognition
- speech signal
- parallel corpus
- out of vocabulary
- source code
- cross lingual
- speech recognition technology
- speech synthesis
- information extraction
- spoken document retrieval
- unknown words
- word alignment
- text retrieval
- language model
- natural language processing
- natural language
- morphological analysis
- english language
- optical character recognition
- information access
- sentence pairs
- question answering
- mono lingual
- document collections