Deep Learning Based Two-dimensional Speaker Localization With Large Ad-hoc Microphone Arrays.
Shupei LiuYijun GongXiao-Lei ZhangXuelong LiPublished in: CoRR (2022)
Keyphrases
- deep learning
- speaker diarization
- automatic speech recognition
- unsupervised learning
- machine learning
- three dimensional
- unsupervised feature learning
- mental models
- speech recognition
- audio visual
- deep architectures
- text classification
- visual information
- viewpoint
- object recognition
- reinforcement learning
- bayesian networks
- data sets