Augmenting Conformers With Structured State-Space Sequence Models For Online Speech Recognition.
Haozhe ShanAlbert GuZhong MengWeiran WangKrzysztof ChoromanskiTara N. SainathPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- state space
- hidden markov models
- acoustic models
- pattern recognition
- automatic speech recognition
- language model
- speech understanding
- speech synthesis
- speech signal
- keyword spotting
- feature extraction
- speech recognition technology
- model selection
- speech recognition errors
- speech retrieval
- audio visual speech recognition