# Dimensional Emotion Recognition on IEMOCAP Source: [Dimensional Emotion Recognition on IEMOCAP]() Collection index: [llms.txt]() Data updated: 2026-06-17T07:33:00.343Z Evaluation of dimensional Emotion Recognition performance on the IEMOCAP dataset, reporting metrics related to Valence, Arousal, and Tension dimensions, including ALAS 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 | Emotion Recognition | | Dataset (including any stated split) | IEMOCAP | | Metric | Count VV | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 - [Count VV](): Higher is better; unit: SCALAR. - [Acc (Arousal)](): Higher is better; unit: PERCENT. - [Acc (Tension)](): Higher is better; unit: PERCENT. - [L\* Score](): Higher is better; unit: SCALAR. - [ALAS Soft (VV)](): Higher is better; unit: SCALAR. - [ALAS Soft (All)](): Higher is better; unit: SCALAR. - [ALAS Hard (VV)](): Higher is better; unit: SCALAR. - [ALAS Hard (All)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Count VV | Result date | Report paper | | --- | --- | --- | --- | | Qwen-Omni | 231 | Not recorded | 68fa79d91e209131cea7fbe6 | | AF3 | 222 | Not recorded | 68fa79d91e209131cea7fbe6 | | Qwen2-Audio | 190 | Not recorded | 68fa79d91e209131cea7fbe6 | | SALMONN | 183 | Not recorded | 68fa79d91e209131cea7fbe6 | ### Qwen-Omni Count VV: 231. Result ID: 6a324d93fbc373592c2f8092. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Streaming-modified Whisper","LLM":"Qwen2.5 Thinker","Adapter":"Learned projection"}. This record does not assert independent reproduction. ### AF3 Count VV: 222. Result ID: 6a324d93fbc373592c2f8090. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"AF-Whisper","LLM":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Qwen2-Audio Count VV: 190. Result ID: 6a324d93fbc373592c2f8091. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Whisper-large-v3","LLM":"Qwen-7B","Adapter":"None"}. This record does not assert independent reproduction. ### SALMONN Count VV: 183. Result ID: 6a324d93fbc373592c2f8093. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Whisper-v2 + BEATs","LLM":"Vicuna-13B","Adapter":"Q-Former"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.