Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition.
Kazuki ShimadaYoshiaki BandoMasato MimuraKatsutoshi ItoyamaKazuyoshi YoshiiTatsuya KawaharaPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2019)
Keyphrases
- speech enhancement
- noisy environments
- automatic speech recognition
- speech signal
- speech recognition
- noise reduction
- linear prediction
- background noise
- speaker identification
- spectral subtraction
- hidden markov models
- broadcast news
- single channel
- additive noise
- signal to noise ratio
- vocal tract
- conversational speech
- non stationary
- acoustic features
- pattern recognition
- feature extraction