# Speech Interruption Handling on SID-Bench English 1.0

Source: [Speech Interruption Handling on SID-Bench English 1.0](<https://www.sota2.com/research/sota/speech-interruption-handling-on-sid-bench-english-1-0>)

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

Data updated: 2026-03-26T14:32:35.580Z

Evaluation of model performance on handling speech interruptions using the SID-Bench English 1.0 dataset, measured by IRL, FIR, and APT scores.

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 | Speech Interruption Handling |
| Dataset (including any stated split) | SID-Bench English 1.0 |
| Metric | IRL |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [IRL](<https://www.sota2.com/research/sota/speech-interruption-handling-on-sid-bench-english-1-0.md?metric=IRL>): Lower is better; unit: SCALAR.

- [FIR](<https://www.sota2.com/research/sota/speech-interruption-handling-on-sid-bench-english-1-0.md?metric=FIR>): Higher is better; unit: PERCENT.

- [APT](<https://www.sota2.com/research/sota/speech-interruption-handling-on-sid-bench-english-1-0.md?metric=APT>): Higher is better; unit: SCALAR.

## Recorded results

| Method | IRL | Result date | Report paper |
| --- | --- | --- | --- |
| FSMN-VAD | 0 | Not recorded | 69c4bdb70636e5bf4afc7774 |
| Free-Omni(Silero VAD) | 0.141 | Not recorded | 69c4bdb70636e5bf4afc7774 |
| SID-model | 0.444 | Not recorded | 69c4bdb70636e5bf4afc7774 |
| FireRedChat (pVAD) | 0.474 | Not recorded | 69c4bdb70636e5bf4afc7774 |
| Moshi | 2.517 | Not recorded | 69c4bdb70636e5bf4afc7774 |

### FSMN-VAD

IRL: 0. Result ID: 69c5436547f34ce924af2edb.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb70636e5bf4afc7774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64231e209131cea02c1b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Free-Omni(Silero VAD)

IRL: 0.141. Result ID: 69c5436547f34ce924af2edc.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb70636e5bf4afc7774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa760a1e209131cea6b0d4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SID-model

IRL: 0.444. Result ID: 69c5436547f34ce924af2edf.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb70636e5bf4afc7774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bdb70636e5bf4afc7774.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FireRedChat (pVAD)

IRL: 0.474. Result ID: 69c5436547f34ce924af2edd.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb70636e5bf4afc7774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b301e209131cea87241.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Moshi

IRL: 2.517. Result ID: 69c5436547f34ce924af2ede.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb70636e5bf4afc7774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75001e209131cea652b7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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