# Spoken Term Detection on LibriSpeech train-clean-100 (In-Vocabulary queries)

Source: [Spoken Term Detection on LibriSpeech train-clean-100 (In-Vocabulary queries)](<https://www.sota2.com/research/sota/spoken-term-detection-on-librispeech-train-clean-100-in-vocabulary-queries>)

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

Data updated: 2026-06-26T08:27:16.385Z

Evaluation of Spoken Term Detection performance using MAP, MRR, and MTWV metrics on the in-vocabulary queries subset (train-clean-100) of the LibriSpeech dataset.

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 | Spoken Term Detection |
| Dataset (including any stated split) | LibriSpeech train-clean-100 (In-Vocabulary queries) |
| Metric | MAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [MAP](<https://www.sota2.com/research/sota/spoken-term-detection-on-librispeech-train-clean-100-in-vocabulary-queries.md?metric=MAP>): Higher is better; unit: PERCENT.

- [MRR](<https://www.sota2.com/research/sota/spoken-term-detection-on-librispeech-train-clean-100-in-vocabulary-queries.md?metric=MRR>): Higher is better; unit: PERCENT.

- [MTWV](<https://www.sota2.com/research/sota/spoken-term-detection-on-librispeech-train-clean-100-in-vocabulary-queries.md?metric=MTWV>): Lower is better; unit: PERCENT.

## Recorded results

| Method | MAP | Result date | Report paper |
| --- | --- | --- | --- |
| wav2tok 2.0 | 86 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| wav2tok 2.0 | 85 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| wav2tok | 82 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| wav2tok | 80 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| wav2tok 2.0 | 78 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| BEST-STD | 73 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| BEST-STD | 71 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| wav2tok | 71 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| BEST-STD | 65 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| Speech Tokenizer | 47 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| Phone Posteriors | 42 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| WavLM-Base | 35 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| MFCC | 30 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| WavLM-Base | 30 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| HuBERT-Base | 22 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| HuBERT-Base | 18 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| BNF | 15 | Not recorded | 6a3e07c4206542251d7cb6d8 |
| Encodec | 15 | Not recorded | 6a3e07c4206542251d7cb6d8 |

### wav2tok 2.0

MAP: 86. Result ID: 6a3e37e2fbc373592c602ada.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

Recorded evaluation configuration: {"Tokens":"512"}. This record does not assert independent reproduction.

### wav2tok 2.0

MAP: 85. Result ID: 6a3e37e2fbc373592c602ad9.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

Recorded evaluation configuration: {"Tokens":"256"}. This record does not assert independent reproduction.

### wav2tok

MAP: 82. Result ID: 6a3e37e2fbc373592c602ad6.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

Recorded evaluation configuration: {"Tokens":"256"}. This record does not assert independent reproduction.

### wav2tok

MAP: 80. Result ID: 6a3e37e2fbc373592c602ad7.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

Recorded evaluation configuration: {"Tokens":"512"}. This record does not assert independent reproduction.

### wav2tok 2.0

MAP: 78. Result ID: 6a3e37e2fbc373592c602adb.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

Recorded evaluation configuration: {"Tokens":"1024"}. This record does not assert independent reproduction.

### BEST-STD

MAP: 73. Result ID: 6a3e37e2fbc373592c602ad4.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c928.md>)

Recorded evaluation configuration: {"Tokens":"512"}. This record does not assert independent reproduction.

### BEST-STD

MAP: 71. Result ID: 6a3e37e2fbc373592c602ad3.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c928.md>)

Recorded evaluation configuration: {"Tokens":"256"}. This record does not assert independent reproduction.

### wav2tok

MAP: 71. Result ID: 6a3e37e2fbc373592c602ad8.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

Recorded evaluation configuration: {"Tokens":"1024"}. This record does not assert independent reproduction.

### BEST-STD

MAP: 65. Result ID: 6a3e37e2fbc373592c602ad5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c928.md>)

Recorded evaluation configuration: {"Tokens":"1024"}. This record does not assert independent reproduction.

### Speech Tokenizer

MAP: 47. Result ID: 6a3e37e2fbc373592c602ad2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fa1e209131cea53de7.md>)

Recorded evaluation configuration: {"Tokens":"1024"}. This record does not assert independent reproduction.

### Phone Posteriors

MAP: 42. Result ID: 6a3e37e2fbc373592c602acb.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

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

### WavLM-Base

MAP: 35. Result ID: 6a3e37e2fbc373592c602acf.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfa1e209131cea3d210.md>)

[Implementation](<https://aka.ms/wavlm>)

Recorded evaluation configuration: {"Tokens":"512"}. This record does not assert independent reproduction.

### MFCC

MAP: 30. Result ID: 6a3e37e2fbc373592c602aca.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62451e209131ce9f86c8.md>)

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

### WavLM-Base

MAP: 30. Result ID: 6a3e37e2fbc373592c602ad0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfa1e209131cea3d210.md>)

[Implementation](<https://aka.ms/wavlm>)

Recorded evaluation configuration: {"Tokens":"1000"}. This record does not assert independent reproduction.

### HuBERT-Base

MAP: 22. Result ID: 6a3e37e2fbc373592c602acd.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea26880.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/master/examples/hubert>)

Recorded evaluation configuration: {"Tokens":"512"}. This record does not assert independent reproduction.

### HuBERT-Base

MAP: 18. Result ID: 6a3e37e2fbc373592c602ace.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea26880.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/master/examples/hubert>)

Recorded evaluation configuration: {"Tokens":"1000"}. This record does not assert independent reproduction.

### BNF

MAP: 15. Result ID: 6a3e37e2fbc373592c602acc.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

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

### Encodec

MAP: 15. Result ID: 6a3e37e2fbc373592c602ad1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e07c4206542251d7cb6d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6db91e209131cea3b969.md>)

Recorded evaluation configuration: {"Tokens":"1024"}. This record does not assert independent reproduction.

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