Speaker Determination in Video News by Using Acoustic Features and Transcripts.
Yasuhiko WatanabeShigeru TojiYoshihiro OkadaPublished in: NLPRS (2001)
Keyphrases
- automatic speech recognition
- acoustic features
- broadcast news
- speech recognition
- audio stream
- speaker verification
- audio features
- speech signal
- speaker identification
- hidden markov models
- mel frequency cepstral coefficients
- news video
- speaker diarization
- visual features
- music information retrieval
- video data
- video content
- visual speech
- keywords
- audio visual
- video sequences
- multimedia
- noisy environments
- genre classification
- video retrieval