AMI corpus
Emerging8papers using it
2021first seen
The AMI corpus is a dataset that contains recordings of multi-speaker meetings, used to evaluate the performance of automatic speech recognition systems in handling overlapping speech.
Papers using AMI corpus (8)
- Domain Adaptation of the Pyannote Diarization Pipeline for Conversational Indonesian AudioCALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASROne model to rule them all ? Towards End-to-End Joint Speaker
Diarization and Speech RecognitionSpeaker Diarization Based on Multi-channel Microphone Array in
Small-scale MeetingUnsupervised Multi-channel Separation and AdaptationGraph Neural Networks for Contextual ASR with the Tree-Constrained
Pointer GeneratorAdapting Speech Separation to Real-World Meetings Using Mixture
Invariant TrainingNeural Blind Source Separation and Diarization for Distant Speech
Recognition