Automatic multimedia indexing: combining audio, speech, and visual information to index broadcast news.
Katsutoshi OhtsukiKatsuji BesshoYoshihiro MatsuoShoichi MatsunagaYoshihiko HayashiPublished in: IEEE Signal Process. Mag. (2006)
Keyphrases
- visual information
- broadcast news
- audio visual
- speech transcripts
- multimedia
- video search
- visual content
- automatic speech recognition
- story segmentation
- visual features
- speaker identification
- multimedia databases
- spoken document retrieval
- visual data
- low level
- spoken documents
- video retrieval
- eye movements
- speaker diarization
- content based retrieval
- multimedia content
- information retrieval
- speech recognition
- news video
- language processing
- spoken term detection
- domain knowledge
- image classification
- video database
- image collections
- multimedia documents
- language model
- video data
- low level features
- temporal information
- multi modal
- audio features
- semantic information
- spontaneous speech
- hidden markov models
- high level