TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
hub Mixed citations
Qwen3-ASR Technical Report
Mixed citation behavior. Most common role is method (56%).
47
Pith papers citing it
Method
56% of classified citations
abstract
In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects. Both of them leverage large-scale speech training data and the strong audio understanding ability of their foundation model Qwen3-Omni. We conduct comprehensive internal evaluation besides the open-sourced benchmarks as ASR models might differ little on open-sourced benchmark scores but exhibit significant quality differences in real-world scenarios. The experiments reveal that the 1.7B version achieves SOTA performance among open-sourced ASR models and is competitive with the strongest proprietary APIs while the 0.6B version offers the best accuracy-efficiency trade-off. Qwen3-ASR-0.6B can achieve an average TTFT as low as 92ms and transcribe 2000 seconds speech in 1 second at a concurrency of 128. Qwen3-ForcedAligner-0.6B is an LLM based NAR timestamp predictor that is able to align text-speech pairs in 11 languages. Timestamp accuracy experiments show that the proposed model outperforms the three strongest force alignment models and takes more advantages in efficiency and versatility. To further accelerate the community research of ASR and audio understanding, we release these models under the Apache 2.0 license.
hub tools
citation-role summary
method 5
background 4
citation-polarity summary
years
2026 47representative citing papers
Introduces the MMEE corpus and shows multilingual training improves robustness of speech emphasis models across languages and emotions while monolingual models transfer poorly.
PolySpeech-100 is a new benchmark for native-level speech comprehension across 110 linguistic variants that evaluates 22 models and reports E2E advantages on dialects, robustness gaps on low-resource languages, and degradation from Chain-of-Thought prompting.
FLARE is a new benchmark with 399 long videos, 87k multimodal clips, and 275k user-style queries for testing audiovisual retrieval under caption and query regimes.
A new multi-accent long-form call-center dialogue dataset for English ASR evaluation shows substantial performance variation across accents and segmentation methods.
Talker-T2AV achieves better lip-sync accuracy, video quality, and audio quality than dual-branch baselines by separating high-level shared autoregressive modeling from modality-specific low-level diffusion refinement in a joint audio-video generation framework.
LLM decoders in speech recognition show no racial bias amplification and fewer repetition hallucinations under degradation than Whisper, with audio encoder design mattering more than model scale for fairness and robustness.
AST enables seamless speech editing by latent recomposition on pre-trained TTS models plus adaptive weak fact guidance, plus a new dataset and WDTW metric, claiming 70% WER reduction and better temporal consistency without training.
Phoneme-based interfaces match or surpass projector-based ones for LLM ASR, especially in low-resource languages, and a BPE-phoneme hybrid offers additional improvements.
YingMusic-Singer-Plus is a diffusion model for singing voice synthesis that preserves melody from a reference clip while allowing flexible lyric changes without manual alignment, outperforming Vevo2 and introducing the LyricEditBench benchmark.
SQuTR aggregates 37k queries from six text retrieval datasets, synthesizes speech from 200 speakers, adds 17 noise categories at varying SNR, and shows that even large retrieval models degrade sharply under extreme acoustic noise.
MemoryCard organizes long videos into self-contained topic-aware Memory Cards that improve long-video QA accuracy by up to 21.8% relative under fixed visual-token budgets.
M2S-AVSR introduces multi-view self-supervised visual encoding and modality-aware fusion for AVSR, releases the AISHELL8-RealScene dataset, and reports relative gains up to 29.4% on LRS3 under perturbations plus new SOTA on MISP2021.
Audio-Interaction unifies offline and online audio tasks into one streaming model via the SoundFlow framework and a new 2.6M-item streaming corpus, enabling real-time instruction following and proactive responses.
READ is a reference-free ASR hypothesis scorer that measures acoustic discrepancy via conditional likelihood from a pretrained auto-regressive TTS model and yields up to 20% relative error rate reduction when used for refinement.
AlignAtt4LLM adapts AlignAtt to decoder-only LLMs via prompt layout, head selection, and attention replay, outperforming IWSLT 2026 baselines for En-De and En-It at ~2s and <4s latency.
LaSR improves context-aware terminology recognition in speech LLMs by aligning latent CoT supervision on acoustic regions and introducing latent reasoning periods, shown on a new academic corpus to outperform standard fine-tuning without added latency.
MindVoice disentangles neural-to-speech reconstruction into semantic and acoustic pathways using pretrained priors, then fuses them with speech generation models to produce intelligible output from non-invasive recordings.
Agentic ASR adds closed-loop semantic correction to ASR and introduces S²ER, an LLM judge for meaning-level errors, showing larger gains on semantic than token metrics across multilingual benchmarks.
A data pipeline, 14-dimension benchmark, and decoupled fine-tuning model are presented to advance fine-grained multi-dimensional speech understanding in LLMs.
VocalParse applies interleaved and Chain-of-Thought prompting to a Large Audio Language Model to jointly transcribe lyrics, melody and word-note alignments, achieving state-of-the-art results on multiple singing datasets.
Current audio-language models fail to use clinical multimodal context for dysarthric speech recognition, but context-aware LoRA fine-tuning delivers large accuracy gains on the SAP dataset.
LaDA-Band applies discrete masked diffusion with dual-track conditioning and progressive training to generate vocal-to-accompaniment tracks that improve acoustic authenticity, global coherence, and dynamic orchestration over prior baselines.
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
citing papers explorer
-
FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
FLARE is a new benchmark with 399 long videos, 87k multimodal clips, and 275k user-style queries for testing audiovisual retrieval under caption and query regimes.
-
Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
A data pipeline, 14-dimension benchmark, and decoupled fine-tuning model are presented to advance fine-grained multi-dimensional speech understanding in LLMs.
-
VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models
VocalParse applies interleaved and Chain-of-Thought prompting to a Large Audio Language Model to jointly transcribe lyrics, melody and word-note alignments, achieving state-of-the-art results on multiple singing datasets.
-
ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
-
Dolphin-CN-Dialect: Where Chinese Dialects Matter
Dolphin-CN-Dialect is a compact ASR model that boosts Chinese dialect accuracy through balanced sampling of rare dialects and character-level tokenization while staying smaller than recent open-source competitors.