AMI

The AMI Meeting Corpus consists of 100 hours of meeting recordings. The recordings use a range of signals synchronized to a common timeline. These include close-talking and far-field microphones, individual and room-view video cameras, and output from a slide projector and an electronic whiteboard. During the meetings,

Papers using AMI (43)

Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams2025 · 2 citesSoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription2026Fast and Robust On-Device Speaker Diarization: Relative Minimum Cluster Size for Stride-Accelerated Pipelines2026Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition2026Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning2026Teaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update2026BiRQ: Bi-Level Self-Labeling Random Quantization for Self-Supervised Speech Recognition2025Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM2025A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport2025Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition2021 · 76 citesInjecting Text in Self-Supervised Speech Pretraining2021 · 25 citesSupervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization2023 · 12 citesAdvancing Multi-talker ASR Performance with Large Language Models2024 · 9 citesGPU-accelerated Guided Source Separation for Meeting Transcription2022 · 5 citesTranscribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR2021 · 3 citesFAST-RIR: Fast neural diffuse room impulse response generator2021 · 3 citesMulti-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition2021 · 3 citesConcurrent Speaker Detection: A multi-microphone Transformer-Based Approach2024 · 3 citesAdapting self-supervised models to multi-talker speech recognition using speaker embeddings2022 · 2 citesProgressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training2024 · 2 citesAsk2Mask: Guided Data Selection for Masked Speech Modeling2022 · 1 citesAdapting Multi-Lingual ASR Models for Handling Multiple Talkers2023 · 1 citesSURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition2023 · 1 citesEnd-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis2023 · 1 citesXLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models2024 · 1 citesSelf-Supervised Metric Learning With Graph Clustering For Speaker Diarization2021All-neural beamformer for continuous speech separation2021Effective Cross-Utterance Language Modeling for Conversational Speech Recognition2021Speech-enhanced and Noise-aware Networks for Robust Speech Recognition2022CycleGAN-Based Unpaired Speech Dereverberation2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition2022ESSumm: Extractive Speech Summarization from Untranscribed Meeting2022G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR2022Spectral Clustering-aware Learning of Embeddings for Speaker Diarisation2022Multitask Detection of Speaker Changes, Overlapping Speech and Voice Activity Using wav2vec 2.02022Speech separation with large-scale self-supervised learning2022Leveraging Cross-Utterance Context For ASR Decoding2023End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization2024On Speaker Attribution with SURT2024Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization2024LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction2024Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models2024Online speaker diarization of meetings guided by speech separation2024