Speaker Diarization Using Stereo Audio Channels: Preliminary Study on Utterance Clustering.
Yingjun DongNeil G. MacLarenYiding CaoFrancis J. YammarinoShelley D. DionneMichael D. MumfordShane ConnellyHiroki SayamaGregory A. RuarkPublished in: CoRR (2020)
Keyphrases
- preliminary study
- speaker diarization
- audio stream
- speech recognition
- bayesian information criterion
- clustering algorithm
- broadcast news
- speaker identification
- k means
- unsupervised learning
- computer vision
- visual information
- multimedia
- hidden markov models
- high dimensional data
- language model
- visual features
- audio visual