# Audio Retrieval on TIMIT

Source: [Audio Retrieval on TIMIT](<https://www.sota2.com/research/sota/audio-retrieval-on-timit>)

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

Data updated: 2026-05-08T11:28:14.783Z

Evaluation of audio retrieval performance on the TIMIT dataset, typically measured using Rank-based metrics (R@k) and Mean Reciprocal Rank (MRR).

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 | Audio Retrieval |
| Dataset (including any stated split) | TIMIT |
| Metric | Rank@1 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Rank@1](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Rank%401>): Higher is better; unit: SCALAR.

- [Rank@5](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Rank%405>): Higher is better; unit: SCALAR.

- [Rank@10](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Rank%4010>): Higher is better; unit: SCALAR.

- [Rank@20](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Rank%4020>): Higher is better; unit: SCALAR.

- [Mean Reciprocal Rank (MRR)](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Mean%20Reciprocal%20Rank%20(MRR)>): Higher is better; unit: SCALAR.

- [Mean False Rejection Rate (Mean FRR)](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Mean%20False%20Rejection%20Rate%20(Mean%20FRR)>): Lower is better; unit: PERCENT.

- [Hit Rate](<https://www.sota2.com/research/sota/audio-retrieval-on-timit.md?metric=Hit%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Rank@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Geometric | 75 | Not recorded | 69fd6e615497b3b670c89794 |
| Geometric | 75 | Not recorded | 69fd6e615497b3b670c89794 |
| Geometric | 75 | Not recorded | 69fd6e615497b3b670c89794 |
| PairAlign | 71 | Not recorded | 69fd6e615497b3b670c89794 |
| PairAlign | 71 | Not recorded | 69fd6e615497b3b670c89794 |
| PairAlign | 71 | Not recorded | 69fd6e615497b3b670c89794 |

### Geometric

Rank@1: 75. Result ID: 69fdc8c147f34ce924e1bcb9.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

Recorded evaluation configuration: {"Relevance definition":"Segment overlap","Training dataset":"LibriSpeech","Ranking method":"normalized edit distance"}. This record does not assert independent reproduction.

### Geometric

Rank@1: 75. Result ID: 69fdc8c147f34ce924e1bcbb.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

Recorded evaluation configuration: {"Relevance definition":"Phoneme exact","Training dataset":"LibriSpeech","Ranking method":"normalized edit distance"}. This record does not assert independent reproduction.

### Geometric

Rank@1: 75. Result ID: 69fdc8c147f34ce924e1bcbd.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

Recorded evaluation configuration: {"Relevance definition":"Phoneme relaxed","Training dataset":"LibriSpeech","Ranking method":"normalized edit distance"}. This record does not assert independent reproduction.

### PairAlign

Rank@1: 71. Result ID: 69fdc8c147f34ce924e1bcba.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

Recorded evaluation configuration: {"Relevance definition":"Segment overlap","Training dataset":"LibriSpeech","Ranking method":"normalized edit distance"}. This record does not assert independent reproduction.

### PairAlign

Rank@1: 71. Result ID: 69fdc8c147f34ce924e1bcbc.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

Recorded evaluation configuration: {"Relevance definition":"Phoneme exact","Training dataset":"LibriSpeech","Ranking method":"normalized edit distance"}. This record does not assert independent reproduction.

### PairAlign

Rank@1: 71. Result ID: 69fdc8c147f34ce924e1bcbe.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e615497b3b670c89794.md>)

Recorded evaluation configuration: {"Relevance definition":"Phoneme relaxed","Training dataset":"LibriSpeech","Ranking method":"normalized edit distance"}. This record does not assert independent reproduction.

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