Acoustic Model Fusion For End-to-End Speech Recognition.
Zhihong LeiMingbin XuShiyi HanLeo LiuZhen HuangTim NgYuanyuan ZhangErnest PusateriMirko HannemannYaqiao DengMan-Hung SiuPublished in: ASRU (2023)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- speech synthesis
- language model
- speech signal
- speech recognition technology
- speech recognizer
- speaker identification
- pattern recognition
- automatic speech recognition
- congestion control
- speech recognition systems
- noisy environments
- speaker independent
- speech recognizers
- multiscale
- isolated word