Lightweight Audio Segmentation for Long-form Speech Translation.
Jaesong LeeSoyoon KimHanbyul KimJoon Son ChungPublished in: CoRR (2024)
Keyphrases
- lightweight
- audio visual
- broadcast news
- audio stream
- speaker identification
- segmentation algorithm
- image segmentation
- text to speech
- speech processing
- multimedia
- segmentation method
- medical images
- speech recognition
- level set
- emotion recognition
- word segmentation
- multi stream
- spoken language
- digital audio
- authentication protocol
- audio recordings
- communication networks
- communication infrastructure
- development environments
- automatic transcription
- cepstral features
- speech synthesis
- acoustic features
- audio signals
- dos attacks
- development environment
- distributed databases
- visual information
- machine translation