Relevant Phonetic-aware Neural Acoustic Models using Native English and Japanese Speech for Japanese-English Automatic Speech Recognition.
Ryo MasumuraSuguru KabashimaTakafumi MoriyaSatoshi KobashikawaYoshikazu YamaguchiYushi AonoPublished in: APSIPA (2018)
Keyphrases
- broadcast news
- automatic speech recognition
- acoustic models
- speech recognition
- speech recognizer
- spoken term detection
- spoken document retrieval
- speech signal
- word error rate
- conversational speech
- hidden markov models
- speaker identification
- speech retrieval
- speech corpus
- speech sounds
- speaker independent
- video search
- spontaneous speech
- noisy environments
- speaker diarization
- discriminative training
- speech recognition systems
- chinese characters
- video retrieval
- machine translation
- language model
- machine learning
- natural language
- neural network
- image processing
- pattern recognition