analiza aiqbench
This research introduces DSSM-CRF, a novel architecture for conversational speech emotion recognition that explicitly disentangles cross-speaker context from within-speaker emotional evolution using state-space models and dynamic CRFs. By treating interlocutor turns as contextual influences rather than direct transitions in another speaker's trajectory, the model achieves significant performance gains on standard benchmarks like IEMOCAP and MELD. The work advances machine learning techniques for handling multi-agent temporal dynamics in audio-only settings without relying on visual inputs.
Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation
arXiv:2608.22399v1 Announce Type: new Abstract: Conversational speech emotion recognition must reconcile acoustic evidence across temporal scales with two interaction processes: cross-speaker contextual influence and within-speaker emotion evolution. We propose DSSM-CRF, an audio-only architecture that explicitly separates these processes. Bidirectional state-space models encode fused self-supervised speech representations at frame and dialogue scales, so each utterance representation captures local prosody and context from all speakers. The decoder then orders each speaker's utterances into an independent dynamic conditional random field chain. Consecutive utterances in a speaker's chain form a transition pair whose score combines a corpus-level transition matrix with a residual predicted from the two contextualized utterances. An auxiliary objective supervises whether each pair changes emotion but does not participate in Viterbi inference. Thus, interlocutor turns affect contextual emotion scores without being treated as transitions in another speaker's emotion trajectory. DSSM-CRF achieves 75.81% UA and 74.90% WA on IEMOCAP, and 54.72% WA and 49.31% WF1 on MELD. Matched controls demonstrate complementary gains from speaker-wise factorization and CRF modeling.
Abstract:Conversational speech emotion recognition must reconcile acoustic evidence across temporal scales with two interaction processes: cross-speaker contextual influence and within-speaker emotion evolution. We propose DSSM-CRF, an audio-only architecture that explicitly separates these processes. Bidirectional state-space models encode fused self-supervised speech representations at frame and dialogue scales, so each utterance representation captures local prosody and context from all speakers. The decoder then orders each speaker's utterances into an independent dynamic conditional random field chain. Consecutive utterances in a speaker's chain form a transition pair whose score combines a corpus-level transition matrix with a residual predicted from the two contextualized utterances. An auxiliary objective supervises whether each pair changes emotion but does not participate in Viterbi inference. Thus, interlocutor turns affect contextual emotion scores without being treated as transitions in another speaker's emotion trajectory. DSSM-CRF achieves 75.81% UA and 74.90% WA on IEMOCAP, and 54.72% WA and 49.31% WF1 on MELD. Matched controls demonstrate complementary gains from speaker-wise factorization and CRF modeling.
5 pages, 2 figures, 4 tables. Submitted to ICASSP 2027
Machine Learning (cs.LG)
arXiv:2608.22399 [cs.LG]
(or arXiv:2608.22399v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.22399 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 264 cuvinte
Subiecte conexe
State of the Field: AI for Epistemics and Coordination
LessWrong · 2 oct. 2026
Problems of Proliferation
LessWrong · 29 sept. 2026
WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion
arXiv · 15 sept. 2026
"I am an AI Safety Researcher"
LessWrong · 23 sept. 2026