Acoustic Model Fusion for End-to-end Speech Recognition.
Zhihong LeiMingbin XuShiyi HanLeo LiuZhen HuangTim NgYuanyuan ZhangErnest PusateriMirko HannemannYaqiao DengMan-Hung SiuPublished in: CoRR (2023)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- speech recognizer
- speech signal
- speech processing
- speech recognition technology
- speech recognition systems
- pattern recognition
- congestion control
- automatic speech recognition
- speech synthesis
- speaker independent
- speaker identification
- speaker dependent
- speech retrieval
- speech recognizers
- isolated word
- non stationary
- video data
- probabilistic model
- bayesian networks