Pith. sign in

REVIEW 17 cited by

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.11013 v1 pith:DFITJTZI submitted 2023-05-18 cs.SD cs.CLeess.AS

Zhifu Gao , Zerui Li , Jiaming Wang , Haoneng Luo , Xian Shi , Mengzhe Chen , Yabin Li , Lingyun Zuo
show 3 more authors
Zhihao Du Zhangyu Xiao Shiliang Zhang
This is my paper · ORCID
classification cs.SDcs.CLeess.AS
keywords speechmodelrecognitionparaformertrainedfunasrindustrialtoolkit
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to deploy them in applications. The toolkit's flagship model, Paraformer, is a non-autoregressive end-to-end speech recognition model that has been trained on a manually annotated Mandarin speech recognition dataset that contains 60,000 hours of speech. To improve the performance of Paraformer, we have added timestamp prediction and hotword customization capabilities to the standard Paraformer backbone. In addition, to facilitate model deployment, we have open-sourced a voice activity detection model based on the Feedforward Sequential Memory Network (FSMN-VAD) and a text post-processing punctuation model based on the controllable time-delay Transformer (CT-Transformer), both of which were trained on industrial corpora. These functional modules provide a solid foundation for building high-precision long audio speech recognition services. Compared to other models trained on open datasets, Paraformer demonstrates superior performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

    cs.AI 2026-03 conditional novelty 6.5 of 10

    SocialOmni jointly evaluates speaker ID, turn-entry timing, and interruption phrasing on 12 OLMs and finds perception accuracy decouples from socially appropriate generation.

  2. Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization

    cs.SD 2026-08 conditional novelty 6.0 of 10

    A jointly trained speech tokenizer and flow-matching decoder achieve strong zero-shot TTS and voice conversion on English and Mandarin, with WER below ground truth in several tests.

  3. NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

    cs.SD 2025-08 unverdicted novelty 6.0 of 10

    A Mandarin speech pipeline that tags non-word vocalizations (laughter, breath, filled pauses) for ASR and controls their generation in TTS, backed by a claimed 573-hour, 174,179-utterance word-level annotated corpus.

  4. DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis

    eess.AS 2025-07 conditional novelty 6.0 of 10

    Reinforcement learning on duration prediction improves intelligibility and speaker similarity in a 4-step distilled text-to-speech model, and teacher-guided sampling recovers prosodic diversity.

  5. Ming-Omni: A Unified Multimodal Model for Perception and Generation

    cs.AI 2025-06 conditional novelty 6.0 of 10

    A single model with modality-specific routing processes image, text, audio, and video inputs and generates text, speech, and images, with public benchmarks reported across all of these abilities.

  6. A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model

    eess.AS 2025-05 conditional novelty 6.0 of 10

    A hierarchical speech enhancement pipeline that estimates semantic tokens first and acoustic tokens second, via a factorized codec and diffusion, improves DNSMOS and downstream TTS speaker similarity in noisy far-fiel...

  7. Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm

    eess.AS 2026-07 conditional novelty 5.0 of 10

    Qwen-Audio-3.0-TTS claims state-of-the-art controllable multilingual text-to-speech across 16 languages and 20 Chinese dialects, using a 12.5 Hz tokenizer and multi-stage RL.

  8. OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detection

    cs.RO 2025-09 reject novelty 5.0 of 10

    OVGrasp integrates YOLO-World open-vocabulary detection, depth-based target selection, and speech-triggered release to control a cable-driven soft exoskeleton for assistive grasping.

  9. AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation

    cs.SD 2025-08 conditional novelty 5.0 of 10

    A single multimodal diffusion transformer generates video-synchronized general audio, speech, and song from flexible combinations of video, text, and lyrics inputs.

  10. Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

    cs.SD 2025-02 conditional novelty 5.0 of 10

    A masked generative model pre-trained on unlabeled speech then fine-tuned per task matches or beats task-specific systems across TTS, voice conversion, speaker extraction, enhancement, and lip-to-speech.

  11. Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech

    cs.CL 2026-07 conditional novelty 4.0 of 10

    Diarization-guided full SFT, synthetic-speech LoRA, and GRPO RL adapt Qwen3-ASR-1.7B to 23.70 average tcpMER on the MLC-SLM 2026 Task 1 development set.

  12. Inference-time Scaling for Diffusion-based Audio Super-resolution

    cs.SD 2025-08 conditional novelty 4.0 of 10

    Generating 120 candidate super-resolved audios and choosing the best by task-specific verifiers improves speech, music, and sound effects over single-sample diffusion output, at 120x compute.

  13. SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A purely algebraic interval-splitting consistency objective trains few-step generative models without JVP computations and recovers MeanFlow's differential identity as a special limit.

  14. RiverEcho: Real-Time Interactive Digital System for Ancient Yellow River Culture

    cs.MM 2025-06 conditional novelty 4.0 of 10

    The authors built a voice-interactive digital human system for ancient Yellow River culture with a curated 20,000-segment knowledge base and showed that RAG improves answer quality.

  15. Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget

    cs.SD 2025-04 conditional novelty 4.0 of 10

    Muyan-TTS, a 3B-parameter LLM-based TTS model trained on 100,000+ hours of podcast audio, produces competitive zero-shot speech and runs at 0.33 seconds of inference per second of speech.

  16. Real-Time Textless Dialogue Generation

    cs.CL 2025-01 conditional novelty 4.0 of 10

    A streaming, textless dialogue model predicts turn-taking actions every 160 ms and generates speech units, improving naturalness over cascaded systems at the cost of lower semantic coherence.

  17. YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls

    cs.SD 2024-12 reject novelty 4.0 of 10

    A video-guided sound effects model with a learnable audio-visual aggregator and multi-modal chain-of-thought module reports strong VGGSound benchmark scores, but its few-shot claim rests on three qualitative samples.

Pith tools