Recent advances in the multi-stream HMM/ANN hybrid approach to noise robust ASR.
Astrid HagenAndrew C. MorrisPublished in: Comput. Speech Lang. (2005)
Keyphrases
- recent advances
- multi stream
- noisy environments
- hidden markov models
- audio visual speech recognition
- audio visual
- speech recognition
- automatic speech recognition
- artificial neural networks
- researchers and practitioners
- noise reduction
- neural network
- multimedia
- signal to noise ratio
- input data
- field of pattern recognition
- data sets