Multimodal Speaker Adaptation of Acoustic Model and Language Model for Asr Using Speaker Face Embedding.
Yasufumi MoriyaGareth J. F. JonesPublished in: ICASSP (2019)
Keyphrases
- speech recognition
- speaker adaptation
- language model
- automatic speech recognition
- word error rate
- speaker dependent
- language modeling
- speaker independent
- n gram
- speech recognizer
- document retrieval
- information retrieval
- probabilistic model
- speech signal
- retrieval model
- noisy environments
- query expansion
- speech synthesis
- speaker identification
- test collection
- broadcast news
- smoothing methods
- multi modal
- query terms
- translation model
- relevance model
- audio visual
- speech recognition systems
- hidden markov models
- statistical machine translation
- acoustic features