An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition.
Bhiksha RajLorenzo TuricchiaBent Schmidt-NielsenRahul SarpeshkarPublished in: EURASIP J. Audio Speech Music. Process. (2007)
Keyphrases
- automatic speech recognition
- noisy environments
- speech recognition
- speech signal
- word error rate
- broadcast news
- noise reduction
- conversational speech
- speaker verification
- speech retrieval
- hidden markov models
- word recognition
- video sequences
- information retrieval
- fourier transform
- image processing
- noise model
- signal to noise ratio
- frequency domain
- neural network
- spoken words