Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech.
Ilya SklyarAnna PiunovaChristian OsendorferPublished in: CoRR (2022)
Keyphrases
- multi party
- recognition engine
- human communication
- word segmentation
- privacy preserving
- image parsing
- numeral strings
- segmentation algorithm
- object recognition
- level set
- recognition rate
- image segmentation
- speech recognition
- segmentation method
- word recognition
- automatic speech recognition systems
- recognition algorithm
- mental states
- data streams
- speech corpus
- description language
- medical images
- pattern recognition
- handwriting recognition
- audio video
- feature extraction
- audio visual
- speech recognition systems
- virtual humans
- domain specific
- search algorithm
- face recognition