LibriMix

LibriMix is a dataset that contains mixed speech recordings of multiple talkers and is used to evaluate multi-talker automatic speech recognition (MT-ASR) systems.

Papers using LibriMix (30)

EEND-SS: Joint End-to-end Neural Speaker Diarization And Speech Separation For Flexible Number Of Speakers2022 · 27 citesA Sidecar Separator Can Convert A Single-talker Speech Recognition System To A Multi-talker One2023 · 16 citesUnified Modeling Of Multi-talker Overlapped Speech Recognition And Diarization With A Sidecar Separator2023 · 9 citesUnifying Diarization, Separation, and ASR with Multi-Speaker Encoder2025 · 6 citesMultiple Choice Learning For Efficient Speech Separation With Many Speakers2024 · 1 citesDistilling LLM Semantic Priors into Encoder-Only Multi-Talker ASR with Talker-Count Routing2026SLM-SS: Speech Language Model for Generative Speech Separation2026Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition2025Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition2025CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models2025An Investigation on Speaker Augmentation for End-to-End Speaker Extraction2025Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection2025EEND-DEMUX: End-to-end Neural Speaker Diarization Via Demultiplexed Speaker Embeddings2023 · 1 citesHypothesis Clustering And Merging: Novel Multitalker Speech Recognition With Speaker Tokens2024A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One2023 · 1 citesNoise-Aware Speech Separation with Contrastive Learning2023 · 1 citesUnified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator2023 · 1 citesEEND-DEMUX: End-to-End Neural Speaker Diarization via Demultiplexed Speaker Embeddings2023 · 1 citesUSEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction2024 · 1 citesIndividualized Conditioning and Negative Distances for Speaker Separation2022Monaural Multi-Speaker Speech Separation Using Efficient Transformer Model2023USED: Universal Speaker Extraction and Diarization2023Selective HuBERT: Self-Supervised Pre-Training for Target Speaker in Clean and Mixture Speech2023Target Speech Extraction with Pre-trained Self-supervised Learning Models2024Serialized Output Training by Learned Dominance2024Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System2024Advancing Multi-talker ASR Performance with Large Language Models2024Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition2024Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens2024Multiple Choice Learning for Efficient Speech Separation with Many Speakers2024