Speech Enhancement Using End-to-End Speech Recognition Objectives.
Aswin Shanmugam SubramanianXiaofei WangMurali Karthick BaskarShinji WatanabeToru TaniguchiDung T. TranYuya FujitaPublished in: WASPAA (2019)
Keyphrases
- end to end
- speech recognition
- speech enhancement
- noisy environments
- speech signal
- noisy speech
- vocal tract
- speech synthesis
- automatic speech recognition
- hidden markov models
- language model
- pattern recognition
- spectral subtraction
- background noise
- speaker identification
- noise reduction
- additive noise
- linear prediction
- machine learning
- image processing
- speaker diarization
- broadcast news
- spectral analysis
- signal to noise ratio