# Target-speaker Automatic Speech Recognition on LibriSpeechMix 2

Source: [Target-speaker Automatic Speech Recognition on LibriSpeechMix 2](<https://www.sota2.com/research/sota/target-speaker-automatic-speech-recognition-on-librispeechmix-2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:11:21.999Z

Evaluation of Target-speaker Automatic Speech Recognition performance on the LibriSpeechMix 2 dataset, measured using tcpWER, DER, and MSCE.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Target-speaker Automatic Speech Recognition |
| Dataset (including any stated split) | LibriSpeechMix 2 |
| Metric | tcpWER (%) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [tcpWER (%)](<https://www.sota2.com/research/sota/target-speaker-automatic-speech-recognition-on-librispeechmix-2.md?metric=tcpWER%20(%25)>): Lower is better; unit: PERCENT.

- [DER (0.25s Collar)](<https://www.sota2.com/research/sota/target-speaker-automatic-speech-recognition-on-librispeechmix-2.md?metric=DER%20(0.25s%20Collar)>): Lower is better; unit: PERCENT.

- [MSCE](<https://www.sota2.com/research/sota/target-speaker-automatic-speech-recognition-on-librispeechmix-2.md?metric=MSCE>): Lower is better; unit: PERCENT.

## Recorded results

| Method | tcpWER (%) | Result date | Report paper |
| --- | --- | --- | --- |
| SE-DiCoW | 2.1 | Not recorded | 69799804a2b28e761d87cb42 |
| SOTA | 2.8 | Not recorded | 69799804a2b28e761d87cb42 |
| SE-DiCoW | 3 | Not recorded | 69799804a2b28e761d87cb42 |

### SE-DiCoW

tcpWER (%): 2.1. Result ID: 699a12b05698665ec4969208.

[Reporting paper](<https://www.sota2.com/research/paper/69799804a2b28e761d87cb42.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69799804a2b28e761d87cb42.md>)

Recorded evaluation configuration: {"Diarization Type":"oracle"}. This record does not assert independent reproduction.

### SOTA

tcpWER (%): 2.8. Result ID: 699a12b05698665ec496920a.

[Reporting paper](<https://www.sota2.com/research/paper/69799804a2b28e761d87cb42.md>)

Recorded evaluation configuration: {"Diarization Type":"DiariZen"}. This record does not assert independent reproduction.

### SE-DiCoW

tcpWER (%): 3. Result ID: 699a12b05698665ec4969209.

[Reporting paper](<https://www.sota2.com/research/paper/69799804a2b28e761d87cb42.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69799804a2b28e761d87cb42.md>)

Recorded evaluation configuration: {"Diarization Type":"DiariZen"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
