SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show no model excels across dimensions and compositional editing is especially difficult
hub
Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
VITA-QinYu is the first expressive end-to-end spoken language model supporting role-playing and singing alongside conversation, trained on 15.8K hours of data and outperforming prior models on expressiveness and conversational benchmarks.
OmniTrace converts token-level signals into span-level cross-modal attributions for open-ended generation in omni-modal LLMs via generation-time tracing.
Step-Audio introduces a 130B-parameter unified speech-text model with open-sourced components for understanding, generation, affordable voice cloning, and dynamic control, claiming SOTA human evaluation results on a new benchmark.
LLM system with paralinguistic cue injection and auxiliary reasoning training reaches 0.802 macro F1 and 0.805 accuracy on three-class speech-based crisis level classification under 5-fold cross-validation.
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.
SQuTR is a large bilingual benchmark of 37,317 synthesized spoken queries under clean/low/medium/high noise, showing that retrieval quality steadily degrades as noise increases.
CLSR is an end-to-end contrastive language-speech retriever using an intermediate text-like conversion step to improve retrieval of relevant segments from long audio for spoken question answering.
Kimi-Audio is an open-source audio foundation model that achieves state-of-the-art results on speech recognition, audio understanding, question answering, and conversation after pre-training on more than 13 million hours of speech, sound, and music data.
PASK introduces the DD-MM-PAS paradigm for streaming proactive agents with intent-aware detection, hybrid memory modeling, and a new real-world benchmark where the IntentFlow model matches top LLMs on latency while finding deeper intents.
A two-stage static-then-dynamic prompt selection strategy using prosodic features, LLM coherence scores, and similarity metrics improves emotion intensity and speaker consistency in zero-shot TTS.
citing papers explorer
-
SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show no model excels across dimensions and compositional editing is especially difficult
-
VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing
VITA-QinYu is the first expressive end-to-end spoken language model supporting role-playing and singing alongside conversation, trained on 15.8K hours of data and outperforming prior models on expressiveness and conversational benchmarks.
-
OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs
OmniTrace converts token-level signals into span-level cross-modal attributions for open-ended generation in omni-modal LLMs via generation-time tracing.
-
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Step-Audio introduces a 130B-parameter unified speech-text model with open-sourced components for understanding, generation, affordable voice cloning, and dynamic control, claiming SOTA human evaluation results on a new benchmark.
-
Speech-based Psychological Crisis Assessment using LLMs
LLM system with paralinguistic cue injection and auxiliary reasoning training reaches 0.802 macro F1 and 0.805 accuracy on three-class speech-based crisis level classification under 5-fold cross-validation.
-
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.
-
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
SQuTR is a large bilingual benchmark of 37,317 synthesized spoken queries under clean/low/medium/high noise, showing that retrieval quality steadily degrades as noise increases.
-
End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering
CLSR is an end-to-end contrastive language-speech retriever using an intermediate text-like conversion step to improve retrieval of relevant segments from long audio for spoken question answering.
-
Kimi-Audio Technical Report
Kimi-Audio is an open-source audio foundation model that achieves state-of-the-art results on speech recognition, audio understanding, question answering, and conversation after pre-training on more than 13 million hours of speech, sound, and music data.
-
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
PASK introduces the DD-MM-PAS paradigm for streaming proactive agents with intent-aware detection, hybrid memory modeling, and a new real-world benchmark where the IntentFlow model matches top LLMs on latency while finding deeper intents.
-
Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS
A two-stage static-then-dynamic prompt selection strategy using prosodic features, LLM coherence scores, and similarity metrics improves emotion intensity and speaker consistency in zero-shot TTS.