AliMeeting
Emerging16papers using it
2022first seen
The 'AliMeeting' dataset is a large-scale conversational dataset used to evaluate end-to-end speaker diarization and recognition systems.
Papers using AliMeeting (15)
- Cross-channel Attention-based Target Speaker Voice Activity Detection: Experimental Results For M2met ChallengeSimultaneous Speech Extraction For Multiple Target Speakers Under The Meeting ScenariosSpeaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASRJoint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and RecognitionSpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone ArraysLightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic TransformGPU-accelerated Guided Source Separation for Meeting TranscriptionSimultaneous Speech Extraction for Multiple Target Speakers under the
Meeting ScenariosAdapting Multi-Lingual ASR Models for Handling Multiple TalkersDiariST: Streaming Speech Translation with Speaker DiarizationOnline Target Speaker Voice Activity Detection for Speaker DiarizationSA-Paraformer: Non-autoregressive End-to-End Speaker-Attributed ASREnd-to-end Online Speaker Diarization with Target Speaker TrackingConcurrent Speaker Detection: A multi-microphone Transformer-Based
ApproachMulti-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment