Speaker Conditioning of Acoustic Models Using Affine Transformation for Multi-Speaker Speech Recognition.
Midia YousefiJohn H. L. HansenPublished in: ASRU (2021)
Keyphrases
- speech recognition
- acoustic models
- affine transformation
- speaker independent
- speech recognizer
- automatic speech recognition
- hidden markov models
- pattern recognition
- speech synthesis
- language model
- feature points
- speaker diarization
- speaker identification
- speaker dependent
- speech signal
- broadcast news
- image registration
- b spline
- computer vision
- speech recognition systems
- speaker recognition
- image matching
- speaker adaptation
- image set
- face recognition