Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding.
Tian-Hao ZhangHaibo QinZhi-Hao LaiSong-Lu ChenQi LiuFeng ChenXinyuan QianXu-Cheng YinPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- cooperative
- speech recognition systems
- speaker independent
- speech recognizers
- hidden markov models
- acoustic models
- speech recognizer
- language model
- speech synthesis
- noisy speech
- speech processing
- speech signal
- pattern recognition
- automatic speech recognition
- speaker identification
- speaker dependent
- noisy environments
- semantic knowledge
- acoustic features
- semantic information
- speech retrieval
- speech recognition technology
- multimedia
- speaker recognition
- machine learning
- semantic search
- mel frequency cepstral coefficients
- probabilistic model
- natural language
- bayesian networks
- computer vision