End-To-End Multi-Modal Speech Recognition with Air and Bone Conducted Speech.
Junqi ChenMou WangXiao-Lei ZhangZhiyong HuangSusanto RahardjaPublished in: ICASSP (2022)
Keyphrases
- multi modal
- end to end
- speech recognition
- speech synthesis
- speech signal
- speech recognizer
- automatic speech recognition
- speech processing
- hidden markov models
- language model
- speech recognition systems
- speaker identification
- speech recognition technology
- noisy environments
- pattern recognition
- high dimensional
- speech recognition errors
- video search
- speaker dependent
- speech recognizers
- isolated word
- audio visual
- acoustic models