VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking.
Quan WangHannah MuckenhirnKevin W. WilsonPrashant SridharZelin WuJohn R. HersheyRif A. SaurousRon J. WeissYe JiaIgnacio Lopez-MorenoPublished in: INTERSPEECH (2019)
Keyphrases
- automatic speech recognition
- speech signal
- speech sounds
- mel frequency cepstral coefficients
- synthesized speech
- speech recognition
- prosodic features
- pattern analysis
- speaker verification
- speaker identification
- text to speech
- speaker recognition
- audio visual
- emotion recognition
- speech synthesis
- vocal tract
- sound source
- noise model
- hidden markov models
- wigner distribution
- empirically derived
- target audience
- human visual system
- speaker diarization
- data sets
- energy distribution
- denoising
- acoustic features
- pattern recognition