Hierarchical Softmax for End-To-End Low-Resource Multilingual Speech Recognition.
Qianying LiuZhuo GongZhengdong YangYuhang YangSheng LiChenchen DingNobuaki MinematsuHao HuangFei ChengChenhui ChuSadao KurohashiPublished in: ICASSP (2023)
Keyphrases
- end to end
- speech recognition
- language model
- speech recognizer
- hidden markov models
- pattern recognition
- speech synthesis
- automatic speech recognition
- speech processing
- speech signal
- congestion control
- noisy environments
- speaker identification
- speech recognition technology
- isolated word
- cross language information retrieval
- speech recognition systems
- speech retrieval
- cross lingual
- digital libraries
- neural network
- image quality
- speaker adaptation
- speech recognizers
- audio visual speech recognition