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.
hub Tool reference
Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio
Tool reference. 71% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
18
Pith papers citing it
Method reference
71% of classified citations
hub tools
citation-role summary
dataset 5
background 2
citation-polarity summary
representative citing papers
V.O.I.C.E is a new taxonomy that organizes synthetic voice risks into five categories and shows how they interact with exposure, visibility, and legal context using empirical incident data.
Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.
Murmur matches single-pass long-context ASR accuracy on AMI-IHM while cutting latency 4.2x by tuning chunk size and using intra-chunk attention sparsity via KV eviction.
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.
MoVE uses specialized LoRA expert adapters and a soft router to translate non-verbal vocalizations in S2ST, reproducing them in 76% of cases versus at most 14% for baselines while scoring highest on naturalness and emotional fidelity.
A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.
StableToken introduces a multi-branch architecture with bit-wise voting to create noise-robust semantic speech tokens, achieving lower Unit Edit Distance and better SpeechLLM robustness than prior single-path tokenizers.
HARNESS introduces Arabic-centric speech foundation models that achieve high efficiency and performance through iterative self-distillation and PCA-based signal compression.
Raon-OpenTTS provides an open 510K-hour curated speech dataset and DiT-based TTS models up to 1B parameters that achieve competitive WER and speaker similarity on benchmarks versus closed models trained on millions of hours.
TextPro-SLM reduces the speech-text modality gap by feeding an LLM backbone with synchronized text tokens and prosody embeddings from WhisperPro, achieving lowest gap scores at 3B/7B scales with roughly 1,000 hours of audio.
A one-step text-to-audio model using energy-distance training and contextual distillation outperforms prior fast baselines on AudioCaps and achieves up to 8.5x faster inference than the multi-step IMPACT system with competitive quality.
The authors introduce LLM-based semantic judgment and an agentic interaction loop that improves semantic fidelity and enables iterative corrections in automatic speech recognition beyond traditional WER.
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.
VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
citing papers explorer
No citing papers match the current filters.