Towards automatic speech recognition without pronunciation dictionary, transcribed speech and text resources in the target language using cross-lingual word-to-phoneme alignment.
Felix StahlbergTim SchlippeStephan VogelTanja SchultzPublished in: SLTU (2014)
Keyphrases
- speech recognition
- cross lingual
- parallel corpus
- machine translation
- word level
- target language
- word alignment
- source language
- automatic speech recognition
- spontaneous speech
- parallel corpora
- machine translation system
- mono lingual
- language independent
- speech synthesis
- bilingual dictionaries
- speech signal
- language model
- language modeling
- speech recognizer
- word pairs
- english text
- hidden markov models
- speaker independent
- word sense
- speech recognition systems
- speaker dependent
- cross language
- cross language information retrieval
- statistical machine translation
- word segmentation
- speaker identification
- text documents
- acoustic models
- natural language processing
- query translation
- translation model
- information extraction
- information retrieval
- speaker adaptation
- pattern recognition
- word recognition
- keywords
- noisy environments
- sentence level
- natural language
- out of vocabulary
- n gram
- document clustering
- news articles
- word sense disambiguation
- broadcast news
- text mining
- text classification
- probabilistic model
- text to speech
- text retrieval