Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition.
Tobias MenneRalf SchlüterHermann NeyPublished in: SLT (2018)
Keyphrases
- automatic speech recognition
- multi channel
- speech recognition
- speech enhancement
- speech signal
- single channel
- hidden markov models
- anti aliasing
- word error rate
- broadcast news
- conversational speech
- noisy environments
- acoustic features
- spoken words
- speech retrieval
- neural network
- speech corpus
- speech sounds
- sound source
- speech synthesis
- recognition errors
- maximum likelihood
- acoustic models
- speaker identification
- frequency domain