LibriVoxDeEn: A Corpus for German-to-English Speech Translation and Speech Recognition.
Benjamin BeilharzXin SunSariya KarimovaStefan RiezlerPublished in: CoRR (2019)
Keyphrases
- speech recognition
- statistical machine translation
- language model
- cross language
- parallel corpus
- parallel corpora
- machine translation system
- machine translation
- cross language information retrieval
- speech recognition technology
- cross lingual
- speech signal
- query translation
- translation model
- speech synthesis
- speech recognizer
- automatic speech recognition
- speech processing
- speaker identification
- hidden markov models
- language independent
- word error rate
- language modeling
- noisy environments
- keyword spotting
- noisy speech
- pattern recognition
- source language
- target language
- speech recognition systems
- handwriting recognition
- isolated word
- recognition engine
- question answering
- speaker independent
- acoustic models
- speech recognition errors
- n gram
- document collections
- speaker dependent
- text classification
- spoken document retrieval
- information extraction
- cepstral coefficients
- probabilistic model
- information retrieval