# Speech Emotion Recognition on IEMOCAP Speaker-Independent (test)

Source: [Speech Emotion Recognition on IEMOCAP Speaker-Independent (test)](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-iemocap-speaker-independent-test>)

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

Data updated: 2026-02-26T06:08:21.517Z

Evaluation of Speech Emotion Recognition performance on the speaker-independent test split of the IEMOCAP dataset, reporting Weighted Accuracy (WA).

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 Emotion Recognition |
| Dataset (including any stated split) | IEMOCAP Speaker-Independent (test) |
| Metric | WA |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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

- [WA](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-iemocap-speaker-independent-test.md?metric=WA>): Higher is better; unit: PERCENT.

## Recorded results

| Method | WA | Result date | Report paper |
| --- | --- | --- | --- |
| PF-hbt-large | 73.01 | Not recorded | 68fa6d901e209131cea3aab8 |
| PF-hbt-large-960h | 72.98 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-hbt-large-960h | 72.71 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-hbt-large | 72.31 | Not recorded | 68fa6d901e209131cea3aab8 |
| Attention Pooling | 71.75 | Not recorded | 68fa6d901e209131cea3aab8 |
| PF-w2v-large | 70.99 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-w2v-large | 70.96 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-w2v-base | 70.75 | Not recorded | 68fa6d901e209131cea3aab8 |
| PF-w2v-base | 70.21 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-hbt-base | 69.83 | Not recorded | 68fa6d901e209131cea3aab8 |
| PF-hbt-base | 69.68 | Not recorded | 68fa6d901e209131cea3aab8 |
| PF-w2v-large-960h | 69.08 | Not recorded | 68fa6d901e209131cea3aab8 |
| PF-w2v-base-960h | 68.34 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-w2v-large-960h | 68.18 | Not recorded | 68fa6d901e209131cea3aab8 |
| Frozen-hbt-large | 67.62 | Not recorded | 68fa6d901e209131cea3aab8 |
| Frozen-w2v-large | 65.64 | Not recorded | 68fa6d901e209131cea3aab8 |
| Frozen-hbt-base | 64.92 | Not recorded | 68fa6d901e209131cea3aab8 |
| EF-w2v-base-960h | 64.2 | Not recorded | 68fa6d901e209131cea3aab8 |
| Frozen-w2v-base | 63.43 | Not recorded | 68fa6d901e209131cea3aab8 |

### PF-hbt-large

WA: 73.01. Result ID: 698fc0ae3a6c314849fb9bfa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"HuBERT","Model scale":"Large","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### PF-hbt-large-960h

WA: 72.98. Result ID: 698fc0ae3a6c314849fb9bfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"HuBERT","Model scale":"Large","ASR fine-tuning":"960h"}. This record does not assert independent reproduction.

### EF-hbt-large-960h

WA: 72.71. Result ID: 698fc0ae3a6c314849fb9bfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"HuBERT","Model scale":"Large","ASR fine-tuning":"960h"}. This record does not assert independent reproduction.

### EF-hbt-large

WA: 72.31. Result ID: 698fc0ae3a6c314849fb9bf9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"HuBERT","Model scale":"Large","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### Attention Pooling

WA: 71.75. Result ID: 698fc0ae3a6c314849fb9c01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

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

### PF-w2v-large

WA: 70.99. Result ID: 698fc0ae3a6c314849fb9bf4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"wav2vec 2.0","Model scale":"Large","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### EF-w2v-large

WA: 70.96. Result ID: 698fc0ae3a6c314849fb9bf3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"wav2vec 2.0","Model scale":"Large","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### EF-w2v-base

WA: 70.75. Result ID: 698fc0ae3a6c314849fb9bef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"wav2vec 2.0","Model scale":"Base","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### PF-w2v-base

WA: 70.21. Result ID: 698fc0ae3a6c314849fb9bf0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"wav2vec 2.0","Model scale":"Base","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### EF-hbt-base

WA: 69.83. Result ID: 698fc0ae3a6c314849fb9bf7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"HuBERT","Model scale":"Base","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### PF-hbt-base

WA: 69.68. Result ID: 698fc0ae3a6c314849fb9bf8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"HuBERT","Model scale":"Base","ASR fine-tuning":"No"}. This record does not assert independent reproduction.

### PF-w2v-large-960h

WA: 69.08. Result ID: 698fc0ae3a6c314849fb9bf6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"wav2vec 2.0","Model scale":"Large","ASR fine-tuning":"960h"}. This record does not assert independent reproduction.

### PF-w2v-base-960h

WA: 68.34. Result ID: 698fc0ae3a6c314849fb9bf2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Partial","Backbone architecture":"wav2vec 2.0","Model scale":"Base","ASR fine-tuning":"960h"}. This record does not assert independent reproduction.

### EF-w2v-large-960h

WA: 68.18. Result ID: 698fc0ae3a6c314849fb9bf5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"wav2vec 2.0","Model scale":"Large","ASR fine-tuning":"960h"}. This record does not assert independent reproduction.

### Frozen-hbt-large

WA: 67.62. Result ID: 698fc0ae3a6c314849fb9c00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf44.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Frozen","Backbone architecture":"HuBERT","Model scale":"Large"}. This record does not assert independent reproduction.

### Frozen-w2v-large

WA: 65.64. Result ID: 698fc0ae3a6c314849fb9bfe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf44.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Frozen","Backbone architecture":"wav2vec 2.0","Model scale":"Large"}. This record does not assert independent reproduction.

### Frozen-hbt-base

WA: 64.92. Result ID: 698fc0ae3a6c314849fb9bff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf44.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Frozen","Backbone architecture":"HuBERT","Model scale":"Base"}. This record does not assert independent reproduction.

### EF-w2v-base-960h

WA: 64.2. Result ID: 698fc0ae3a6c314849fb9bf1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Implementation](<https://github.com/speechbrain/speechbrain/tree/develop/recipes>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Entire","Backbone architecture":"wav2vec 2.0","Model scale":"Base","ASR fine-tuning":"960h"}. This record does not assert independent reproduction.

### Frozen-w2v-base

WA: 63.43. Result ID: 698fc0ae3a6c314849fb9bfd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d901e209131cea3aab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf44.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Frozen","Backbone architecture":"wav2vec 2.0","Model scale":"Base"}. This record does not assert independent reproduction.

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