Self-Convolution for Automatic Speech Recognition.
Tianhao ZhangQi LiuXinyuan QianSong-Lu ChenFeng ChenXu-Cheng YinPublished in: ICASSP (2023)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- word error rate
- broadcast news
- image processing
- conversational speech
- speech retrieval
- spoken words
- recognition errors
- word recognition
- pattern recognition
- noisy environments
- language model
- speech sounds
- visual features
- acoustic features
- spontaneous speech
- denoising
- speech corpus
- neural network