A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation.
Yosuke HiguchiNanxin ChenYuya FujitaHirofumi InagumaTatsuya KomatsuJaesong LeeJumon NozakiTianzi WangShinji WatanabePublished in: ASRU (2021)
Keyphrases
- autoregressive
- text generation
- natural language generation
- moving average
- speech recognition
- non stationary
- natural language
- dialogue system
- gaussian markov random field
- theorem prover
- speech signal
- random fields
- sar images
- autoregressive model
- spectrum analysis
- autoregressive moving average
- natural images
- least squares
- image processing
- information retrieval