AMI

The AMI dataset is a collection of annotated meeting recordings used to evaluate speech recognition systems, particularly in the context of unsupervised domain adaptation.

Papers using AMI (32)

Multitask Detection Of Speaker Changes, Overlapping Speech And Voice Activity Using Wav2vec 2.02022 · 13 citesScaling Multi-Talker ASR with Speaker-Agnostic Activity Streams2025 · 2 citesSpeaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization2024 · 1 citesTeaching 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 WavLM2025DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition2025 · 1 citesTree-constrained Pointer Generator With Graph Neural Network Encodings For Contextual Speech Recognition2022 · 7 citesEnd-to-end Multichannel Speaker-attributed ASR: Speaker Guided Decoder And Input Feature Analysis2023 · 5 citesGPU-accelerated Guided Source Separation for Meeting Transcription2022 · 5 citesAdapting self-supervised models to multi-talker speech recognition using speaker embeddings2022 · 2 citesSupervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization2023 · 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 citesTree-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 SURT2024Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training2024Concurrent Speaker Detection: A multi-microphone Transformer-Based Approach2024Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization2024Advancing Multi-talker ASR Performance with Large Language Models2024LS-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