GL-SSD: Global and Local Speech Style Disentanglement by vector quantization for robust sentence boundary detection in speech stream.
Kuncai ZhangWei ZhouPengcheng ZhuHaiqing ChenPublished in: INTERSPEECH (2023)
Keyphrases
- vector quantization
- boundary detection
- speaker recognition
- image compression
- speech recognition
- vector quantizer
- audio visual
- speech signal
- fractal image compression
- reduced complexity
- gaussian mixture model
- distortion measure
- noisy environments
- broadcast news
- image segmentation
- speaker verification
- entropy constrained
- detection algorithm
- input vector
- finite state vector quantization
- speaker identification
- subband
- object recognition