Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire.
Zhiyun FanZhenlin LiangLinhao DongYi LiuShiyu ZhouMeng CaiJun ZhangZejun MaBo XuPublished in: CoRR (2022)
Keyphrases
- change detection
- speech recognition
- speaker recognition
- audio visual
- speaker verification
- automatic speech recognition
- speaker identification
- speaker diarization
- remote sensing
- prosodic features
- remote sensing images
- speaker dependent
- data streams
- satellite imagery
- remotely sensed
- remotely sensed images
- speech signal
- satellite images
- synthesized speech
- hidden markov models
- land cover
- vocal tract
- automatic transcription
- land cover change
- remote sensing imagery
- multimedia
- speech synthesis
- acoustic features
- speech sounds
- shot change detection
- gaussian mixture model
- neural network
- text to speech
- automatic speech recognition systems
- hyperspectral
- frame difference
- multispectral
- man made structures
- image registration
- feature extraction