Amplitude modulation spectrogram based features for robust speech recognition in noisy and reverberant environments.
Niko MoritzJörn AnemüllerBirger KollmeierPublished in: ICASSP (2011)
Keyphrases
- speech recognition
- speech signal
- noisy environments
- automatic speech recognition
- speech recognition systems
- cepstral coefficients
- hidden markov models
- speech processing
- speaker identification
- mel frequency cepstral coefficients
- amplitude modulation
- language model
- speech synthesis
- speech recognizer
- speech recognition technology
- speaker dependent
- speech recognizers
- feature vectors
- feature extraction
- image processing
- speaker recognition
- feature set
- face recognition
- computer vision
- information retrieval