---
title: 'Libri2Mix: 2-Speaker Benchmark'
url: https://www.emergentmind.com/topics/libri2mix
type: topic
---

# Libri2Mix: 2-Speaker Benchmark

Libri2Mix is a simulated 2-speaker mixture corpus within the LibriMix family, derived from LibriSpeech and WHAM, and used as a standard benchmark for monaural speech separation, target speaker extraction (TSE), target-speaker automatic speech recognition (TS-ASR), and related multi-speaker tasks. Across the literature, Libri2Mix appears in clean and noisy conditions, 8 kHz and 16 kHz releases, and both `min` and `max` mixture modes, with `train-100`, `train-360`, development, and test splits serving as recurring evaluation conventions [2304.07142][2203.07960][2406.07461].

## 1. Definition and corpus construction

Libri2Mix is repeatedly described as a simulated 2-speaker mixture corpus derived from LibriSpeech and WHAM. In one formulation, “speech samples come from the LibriSpeech corpus and noise samples come from the WHAM corpus,” and LibriMix uses LUFS rather than SSR to set loudness: speaker loudness lies between \(-25\) and \(-33\) LUFS, while noise loudness lies between \(-38\) and \(-30\) LUFS [2304.07142]. In another formulation oriented toward separation, the benchmark includes a `sep_clean` condition with two speakers only and a `sep_noisy` condition with additive WHAM! noise, using the “16kHz min” version of LibriMix [2203.07960].

Published descriptions of corpus scale depend on which LibriMix subset is being used. A broader clean two-speaker description reports 64,700 training mixtures (about 270 hours), 3,000 development mixtures (about 11 hours), and 3,000 test mixtures (about 11 hours), with average mixture duration 14.8 s [2202.09995]. By contrast, several `train-100` protocols report 13,900 training mixtures, 3,000 validation mixtures, and 3,000 evaluation or test mixtures, reflecting the smaller Libri2Mix-100 configuration frequently used in TSE and TS-ASR studies [2305.16286][2410.16059].

The corpus is therefore not a single immutable release in experimental practice. It is better understood as a standardized mixture-generation framework whose instantiations differ by sampling rate, overlap convention, noise condition, and training subset.

## 2. Configurations, subsets, and protocol variation

A common misconception is that “Libri2Mix” denotes one fixed protocol. In practice, papers use materially different Libri2Mix configurations, and cross-paper comparisons are only meaningful when those choices are aligned.

| Configuration | Characteristics | Representative use |
|---|---|---|
| Clean, `min`, 16 kHz | Two speakers, no added noise | Separation, TSE, SSL probing [2203.07960][2402.13200][2410.16059] |
| Noisy, `min`, 16 kHz | Two speakers plus WHAM! noise | Noise-robust separation, TS-ASR, generative TSE [2305.16286][2505.19314] |
| 8 kHz protocols | Often used to match earlier Conv-TasNet/DPRNN/SepFormer settings | Separation and TSE baselines [2406.07461][2306.16250] |
| `max`, 100% overlap | Full-length overlap, chosen for joint SD/SS/ASR and long-form separation studies | Unified modeling and chunk-wise inference [2508.20474][2607.06088] |
| MC-Libri2Mix | 4-channel reverberant extension of Libri2Mix | Localized TSE and spatial modeling [2202.09995] |

Subset usage is similarly heterogeneous. In one noisy-separation protocol, `train-360` is about 212 hours and `train-100` about 58 hours, with development and test each about 11 hours [2406.07461]. In several 16 kHz `train-100` protocols, the same split is identified instead by utterance count rather than hours, namely 13,900 training mixtures [2305.16286][2410.16059].

The sampling-strategy literature adds an important caveat: Libri2Mix `train-100` and test do not have matched signal-length statistics. One study reports a difference in mean mixture length of 6.2 s and a difference in standard deviation of 1.79 s between `train-100` and test [2304.07142]. This has direct consequences for cropping, batching, and claims about training-efficiency trade-offs.

## 3. Task formulations built on Libri2Mix

Libri2Mix supports several distinct problem formulations. In noisy two-speaker separation, the observation model is written as
$$
\mathbf{y} = \mathbf{n} + \sum_{k=1}^{K} \mathbf{s}_k,\qquad K=2,
$$
with single-channel mixtures and clean source references available for supervised training and intrusive evaluation [2406.07461]. In blind separation studies, the benchmark is therefore used to estimate both speakers from one waveform, usually with PIT-based objectives [2203.07960][2309.12608].

In TSE, the same corpus is reinterpreted as a speaker-conditioned extraction problem. A typical formulation is
$$
\mathbf{y} = \mathbf{x} + \mathbf{i},
$$
where \(\mathbf{x}\) is the target speaker and \(\mathbf{i}\) is the interfering speech or interference mixture, and an auxiliary enrollment utterance identifies which speaker should be recovered [2402.13200]. In several TSE protocols, each 2-speaker mixture is used twice, once with speaker A as target and once with speaker B as target [2202.09995][2410.16059].

Libri2Mix also underpins TS-ASR. In that setting, the model consumes the mixture waveform and a same-speaker enrollment utterance, then predicts only the target speaker’s transcription, sometimes without any explicit separation module [2305.16286]. Later work adapts foundation models such as Whisper to this setting and continues to use noisy Libri2Mix as the main simulated benchmark [2412.05589].

The benchmark has also been extended structurally. MC-Libri2Mix converts the original anechoic mixtures into a 4-channel reverberant corpus using a linear 4-microphone array with 5 cm spacing, pyroomacoustics-generated room impulse responses, room dimensions sampled from \([5,10]\) m in length and width and \([3,4]\) m in height, and \(RT_{60}\) between 200 and 600 ms [2202.09995]. More recent work further embeds Libri2Mix into joint diarization-separation-ASR training or into multi-condition PSE-style tasks such as `mix_single`, `mix_clean`, and `mix_both` [2508.20474][2512.04945].

## 4. Evaluation methodology and common metrics

Because Libri2Mix provides clean source references, it supports a broad range of intrusive metrics. Separation and TSE papers routinely report SI-SDRi or SI-SNRi, PESQ, and ESTOI or STOI [2406.07461][2410.16059]. Some TSE work also defines extraction accuracy as the proportion of utterances with SI-SDRi greater than 1 dB [2410.16059].

Non-intrusive quality measures are also common. NISQA MOS is used in noisy separation studies on Libri2Mix to quantify reference-free speech quality [2406.07461], while DNSMOS P.835 appears in recent generative TSE work [2505.19314][2603.10701]. When Libri2Mix is paired with downstream applications, additional task-specific metrics enter the protocol: WER for TS-ASR [2305.16286][2412.05589], cpWER for chunk-wise blind separation with downstream ASR [2607.06088], EER for speaker verification after separation [2607.06088], and DER for diarization in joint SD/SS/ASR systems [2508.20474].

Enrollment handling is another recurring methodological variable. Several TSE and TS-ASR works follow the SpeakerBeam-style informed protocol, using a clean utterance from the same speaker as enrollment, with official or pre-defined enrollment lists for development and test, and random same-speaker enrollment selection during training [2204.07375][2305.16286][2402.13200]. This matters because Libri2Mix scores can depend not only on the mixture condition but also on how enrollment audio is sampled, cropped, or augmented.

## 5. Representative empirical results

Reported Libri2Mix numbers span multiple tasks and are not directly interchangeable across configurations. Even so, they illustrate why the corpus has become a reference point across separation, extraction, ASR, and unified multi-speaker modeling.

| Setting | Reported result on Libri2Mix | Source |
|---|---|---|
| Blind speech separation | 20.4 dB SI-SDRi | [2309.12608] |
| Noisy separation with generative correction | 12.98 dB SI-SNRi on Libri2Mix noisy test | [2406.07461] |
| Clean TSE with multi-level speaker representation | 15.91 dB SI-SDRi and 97.02% extraction accuracy | [2410.16059] |
| 8 kHz TSE with MC-SpEx | 14.61 dB SI-SDR, PESQ 3.195, ESTOI 84.9% | [2306.16250] |
| Generative TSE with SoloSpeech | PESQ 1.89, ESTOI 0.78, SI-SNR 11.12 dB, WER 0.15, SIM 0.96 | [2505.19314] |
| TS-ASR with SQ-Whisper | 14.6% WER on noisy Libri2Mix test | [2412.05589] |
| Joint SD/SS/ASR with UME | 1.37% DER on Libri2Mix evaluation set | [2508.20474] |

Several trends emerge from these results. First, Libri2Mix remains a strong discriminator among architectural choices. For example, SPGM reported 20.4 dB SI-SDRi on Libri2Mix, exceeding SepFormer by 0.3 dB while matching more parameter-heavy models on this benchmark [2309.12608]. Second, the corpus is central to the evaluation of generative refiners and one-step generators: Fast-GeCo improved SepFormer from 10.58 dB to 12.98 dB SI-SNRi on the noisy test set [2406.07461], while AlphaFlowTSE reported 19.17 dB SI-SDR on clean Libri2Mix and 13.16 dB on noisy Libri2Mix together with PESQ 3.27 and 2.28 for clean and noisy conditions, respectively [2603.10701].

Third, Libri2Mix is not only a signal-level benchmark. It is increasingly used to quantify downstream robustness. Earlier weakly supervised pre-training work reported 24.8%–24.9% WER for TS-HuBERT on noisy Libri2Mix test, improving over WavLM Base + cLN at 27.5% [2305.16286]. More recent TS-ASR adaptation with SQ-Whisper reduced noisy Libri2Mix test WER to 14.6% when `train-360` and speed perturbation were added [2412.05589]. This shift from SI-SDR-centric evaluation toward ASR, SV, and diarization endpoints is a notable feature of current Libri2Mix usage.

## 6. Limitations, extensions, and benchmark significance

Libri2Mix is synthetic, and that remains its defining limitation. Multiple papers note that it is built from LibriSpeech read speech and, in noisy variants, WHAM! noise, so it does not cover all real-world acoustic conditions, richer noise types, stronger reverberation, moving sources, or spontaneous conversational speech [2406.07461][2505.19314][2603.10701]. The benchmark’s statistical mismatch between `train-100` and test length distributions adds a further caveat for studies of cropping, sampling, and efficiency [2304.07142].

At the same time, Libri2Mix has proved unusually extensible. MC-Libri2Mix adds multichannel reverberation and explicit spatial structure [2202.09995]. Three-condition PSE-style tasks reinterpret it as `mix_single`, `mix_clean`, and `mix_both`, enabling universal TSE studies across one-speaker-plus-noise, two-speaker, and two-speaker-plus-noise conditions [2512.04945]. Joint modeling work further embeds Libri2Mix within broader LibriMix settings that include 100% overlap and `max` mode for simultaneous diarization, separation, and ASR [2508.20474].

This suggests that Libri2Mix functions less as a single benchmark file tree than as a benchmark family: a controlled synthetic substrate on which different communities test local feature modeling, speaker conditioning, generative transport, chunk-wise inference, diarization heads, and downstream ASR/SV behavior. Its continuing value lies precisely in that role. It provides enough control for rigorous ablation, enough scale for modern pretrained models, and enough protocol diversity to expose when a method is exploiting a narrow configuration rather than learning a robust multi-speaker representation.

Source: https://www.emergentmind.com/topics/libri2mix