Libri-2Mix

Libri2Mix is a dataset used to evaluate Target Speaker Extraction (TSE) performance by providing mixed speech recordings from the LibriSpeech dataset.

Papers using Libri-2Mix (39)

Investigating Self-supervised Learning For Speech Enhancement And Separation2022 · 61 citesAdapting Self-supervised Models To Multi-talker Speech Recognition Using Speaker Embeddings2022 · 28 citesMc-spex: Towards Effective Speaker Extraction With Multi-scale Interfusion And Conditional Speaker Modulation2023 · 18 citesWeakly-supervised Speech Pre-training: A Case Study On Target Speech Recognition2023 · 12 citesSoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline2025 · 12 citesUnifying Diarization, Separation, and ASR with Multi-Speaker Encoder2025 · 6 citesU-mamba-net: A Highly Efficient Mamba-based U-net Style Network For Noisy And Reverberant Speech Separation2024 · 3 citesSpeaker-aware Mixture Of Mixtures Training For Weakly Supervised Speaker Extraction2022 · 3 citesSEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation2025 · 1 citesTowards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model2026AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow2026TripleC Learning and Lightweight Speech Enhancement for Multi-Condition Target Speech Extraction2025MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean Flow2025GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model2025A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References2025Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios2025Elevating Robust Multi-talker ASR By Decoupling Speaker Separation And Speech Recognition2025Elevating Robust Multi-Talker ASR by Decoupling Speaker Separation and Speech Recognition2025Mvnet: Memory Assistance And Vocal Reinforcement Network For Speech Enhancement2022SPGM: Prioritizing Local Features For Enhanced Speech Separation Performance2023SPMamba: State-space model is all you need in speech separation2024 · 8 citesAdapting self-supervised models to multi-talker speech recognition using speaker embeddings2022 · 2 citesScaling strategies for on-device low-complexity source separation with Conv-Tasnet2023 · 2 citesSQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR2024 · 2 citesUnifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation2023 · 1 citesOn Data Sampling Strategies for Training Neural Network Speech Separation Models2023 · 1 citesWeakly-Supervised Speech Pre-training: A Case Study on Target Speech Recognition2023 · 1 citesMC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation2023 · 1 citesMossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation2023 · 1 citesMVNet: Memory Assistance and Vocal Reinforcement Network for Speech Enhancement2022AudioSlots: A slot-centric generative model for audio separation2023Target Speech Extraction with Conditional Diffusion Model2023SPGM: Prioritizing Local Features for enhanced speech separation performance2023Probing Self-supervised Learning Models with Target Speech Extraction2024Noise-robust Speech Separation with Fast Generative Correction2024On the effectiveness of enrollment speech augmentation for Target Speaker Extraction2024Wanna hear your voice? A sample is all we need!2024Multi-Level Speaker Representation for Target Speaker Extraction2024U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation2024