The paper introduces a de‑identified corpus of 33 in‑person cognitive assessment conversations, comprising 8,250 utterances annotated for three speaker roles and 56 dialogue acts. The authors benchmark large language models on fine‑grained dialogue‑act classification and next‑patient‑utterance generation, finding that instruction tuning and reasoning‑aware fine‑tuning improve performance but that models still struggle with closely related dialogue acts. The corpus and benchmark are presented as tools to measure interaction structure in cognitive assessments and to support future research on conversational markers, clinician education, and validated simulated patients.
By Vishalakshi Arumugam, Dan Schumacher, Veronica Rammouz, Erfan Nourbakhsh, Enrique Gonzalez Guerrero, Jeremy Davis, Anthony Rios
TalkFa introduces a unified benchmark for Farsi dialogue generation and understanding, comprising three datasets: WIKI‑FADIAL (4.2K Wikipedia‑grounded dialogues), DAILYDIALOG‑FA (6.6K dialogues with dialogue‑act and emotion annotations), and PLAYDIAL‑FA (2.1K theatrical dialogues with sentiment labels). All dialogues are curated through multi‑stage review by native speakers, ensuring high quality. Experiments show that LoRA fine‑tuning improves generation performance with less data, while specific models excel on classification tasks, and human evaluation confirms the benchmark’s reliability.
By Neda Jamshidi, Kamyar Zeinalipour, Fahimeh Akbari, Monica Bianchini, Marco Maggini, Marco Gori
The study investigates how automatic speech recognition (ASR) transcript normalization—specifically the removal of filled pauses, punctuation, and colloquial expansions—affects dialogue act classification. By testing nine transcript conditions across six classifiers and three conversational corpora, the authors find that heavy normalization consistently lowers Macro‑F1 scores, especially when using a comprehensive filler lexicon. Punctuation removal and selective filler removal also degrade performance, indicating that the impact of normalization varies with preprocessing choices, feature extraction methods, and the conversational context.
By Lucky Onyekwelu-Udoka, Md Shafiqul Islam
The paper introduces a method for forecasting conversational derailment by incorporating speech act information as an auxiliary signal to enhance pragmatic representations. This approach aims to reduce lexical noise and improve generalizability, especially in low-data and cross-domain scenarios. Experiments on three datasets demonstrate performance gains over existing methods.
By Angela Yifei Yuan, Christine De Kock, Christopher Leckie
DiaRelay introduces a lightweight adapter that lets large language models maintain a constant‑size dialogue‑level memory for emotion recognition in conversation. It builds on LoRA by adding a Selective Relay Memory Transition that aggregates useful historical evidence into a bounded memory, and a Dual‑axis Relay Memory Read that uses this memory to modulate low‑rank feature transformations. Experiments show DiaRelay achieves state‑of‑the‑art weighted F1 and accuracy on MELD with only 7.1 M additional trainable parameters, while also performing competitively on IEMOCAP.
By Zihao Zhou, Bin Yang, Jinghui Qin, Kebing Jin
The paper introduces DSSM-CRF, an audio‑only architecture for conversational speech emotion recognition that separates cross‑speaker contextual influence from within‑speaker emotion evolution. It uses bidirectional state‑space models to encode fused self‑supervised speech representations at both frame and dialogue scales, then orders each speaker’s utterances into an independent dynamic conditional random field chain. The model achieves state‑of‑the‑art performance on IEMOCAP and MELD, with complementary gains from speaker‑wise factorization and CRF modeling.
By Guan-Hua Wen, Hou-Chiang Tseng, Kuan-Yu Chen