Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition.
Aswin Shanmugam SubramanianChao WengShinji WatanabeMeng YuDong YuPublished in: Comput. Speech Lang. (2022)
Keyphrases
- speech recognition
- source localization
- deep learning
- hidden markov models
- pattern recognition
- speech recognizer
- language model
- data mining
- active learning
- speech synthesis
- speech recognition systems
- neural network
- automatic speech recognition
- multi modal
- image classification
- reinforcement learning
- e learning
- computer vision