Web Data Selection Based on Word Embedding for Low-Resource Speech Recognition.
Chuandong XieWu GuoGuoping HuJunhua LiuPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- web data
- speech recognition systems
- speech recognizer
- wall street journal corpus
- web mining
- keyword spotting
- speech recognizers
- language model
- hidden markov models
- semi structured
- pattern recognition
- speech signal
- automatic speech recognition
- speech synthesis
- web pages
- web content
- n gram
- speaker identification
- web documents
- speech recognition technology
- handwriting recognition
- knowledge representation
- computer vision
- information extraction
- probabilistic model
- co occurrence
- website
- speaker independent
- multimedia