Waveform-Domain Speech Enhancement Using Spectrogram Encoding for Robust Speech Recognition.
Hao ShiMasato MimuraTatsuya KawaharaPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- speech recognition
- speech signal
- noisy environments
- speech enhancement
- automatic speech recognition
- noisy speech
- vocal tract
- speaker identification
- pattern recognition
- speech synthesis
- hidden markov models
- background noise
- spectral subtraction
- language model
- linear prediction
- additive noise
- spectral analysis
- speaker recognition
- acoustic features
- single channel
- frequency domain
- multi modal