Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition.
Lei LiuLi LiuHaizhou LiPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech synthesis
- noisy environments
- multi modal fusion
- automatic speech recognition
- speech processing
- speech recognition technology
- speech understanding
- speaker identification
- pattern recognition
- speech recognition systems
- speech recognition errors
- speech signal
- speech recognizer
- speaker independent
- acoustic models
- speaker dependent
- speech retrieval
- speech recognizers
- information retrieval
- non stationary
- training data
- image sequences