SpeechCombine produces instruction-following SLMs via speech pre-training followed by direct weight combination with the text LLM instruction delta, without any speech instruction tuning.
Osum-echat: Enhancing end-to- end empathetic spoken chatbot via understanding-driven spoken dialogue
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8representative citing papers
SpeechParaling-Bench is a new evaluation framework for paralinguistic-aware speech generation that reveals major limitations in current large audio-language models.
HumDial-EIBench is a new benchmark using real human dialogues to evaluate audio language models on emotional intelligence tasks including multi-turn tracking, causal reasoning, empathy generation, and acoustic-semantic conflict resolution.
Sympatheia introduces a continuous affect-conditioned speech dialogue model and the Sympatheia-18k synthetic dataset, showing improved emotional appropriateness over baselines when speech cues are limited.
A new HumDial-FDBench benchmark and real human-recorded dual-channel dataset are released to assess full-duplex dialogue systems on interruptions and conversational flow.
FastTurn fuses streaming CTC semantics with acoustic cues for lower-latency, more accurate turn detection in full-duplex dialogue and releases a real-dialogue test set.
CogAudio-LLM introduces LIME-440K dataset, EIPS chain-of-thought reasoning, and DR-SAPO optimization to address semantic dominance and improve affective responses in audio language models.
PRISM proposes a multi-agent system decoupling speech-to-prosody handling, LLM-based response generation, and synthesis, reporting metric improvements in empathy and prosodic fit for spoken dialogue.
citing papers explorer
-
Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
SpeechCombine produces instruction-following SLMs via speech pre-training followed by direct weight combination with the text LLM instruction delta, without any speech instruction tuning.
-
SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation
SpeechParaling-Bench is a new evaluation framework for paralinguistic-aware speech generation that reveals major limitations in current large audio-language models.
-
HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models
HumDial-EIBench is a new benchmark using real human dialogues to evaluate audio language models on emotional intelligence tasks including multi-turn tracking, causal reasoning, empathy generation, and acoustic-semantic conflict resolution.
-
Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning
Sympatheia introduces a continuous affect-conditioned speech dialogue model and the Sympatheia-18k synthetic dataset, showing improved emotional appropriateness over baselines when speech cues are limited.
-
Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge
A new HumDial-FDBench benchmark and real human-recorded dual-channel dataset are released to assess full-duplex dialogue systems on interruptions and conversational flow.
-
FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection
FastTurn fuses streaming CTC semantics with acoustic cues for lower-latency, more accurate turn detection in full-duplex dialogue and releases a real-dialogue test set.
-
Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models
CogAudio-LLM introduces LIME-440K dataset, EIPS chain-of-thought reasoning, and DR-SAPO optimization to address semantic dominance and improve affective responses in audio language models.
-
PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue
PRISM proposes a multi-agent system decoupling speech-to-prosody handling, LLM-based response generation, and synthesis, reporting metric improvements in empathy and prosodic fit for spoken dialogue.