Pith. sign in

REVIEW 13 cited by

Efficient Training of Audio Transformers with Patchout

Not yet reviewed by Pith; the record is open.

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 2110.05069 v3 pith:ODYMEM4B submitted 2021-10-11 cs.SD cs.LGeess.AS

classification cs.SDcs.LGeess.AS
keywords transformersaudiocnnsmodelsperformanceworkcomplexitypropose
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform Convolutional Neural Networks (CNNs) on vision and audio tasks. However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity. In transformers, the compute and memory complexity is known to grow quadratically with the input length. Therefore, there has been extensive work on optimizing transformers, but often at the cost of degrading predictive performance. In this work, we propose a novel method to optimize and regularize transformers on audio spectrograms. Our proposed models achieve a new state-of-the-art performance on Audioset and can be trained on a single consumer-grade GPU. Furthermore, we propose a transformer model that outperforms CNNs in terms of both performance and training speed. Source code: https://github.com/kkoutini/PaSST

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. Conditional Flow Matching for Visually-Guided Acoustic Highlighting

    eess.AS 2026-02 conditional novelty 6.0 of 10

    Conditional flow matching with a rollout loss and early audio-visual fusion achieves state-of-the-art results on visually-guided acoustic highlighting.

  2. UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A unified audio-video generator built by stitching pre-trained video and music diffusion models, trained on 7,600 hours of data, with a new evaluation benchmark.

  3. MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners

    cs.SD 2025-06 conditional novelty 6.0 of 10

    A lightweight adapter that adds rotary position embeddings to decoupled cross-attention enables efficient time-varying style control and audio inpainting/outpainting for text-to-music diffusion Transformers.

  4. Video-Guided Text-to-Music Generation Using Public Domain Movie Collections

    cs.SD 2025-06 conditional novelty 6.0 of 10

    OSSL is the first self-hosted, mood-annotated video-music dataset, and a video adapter on MusicGen-Medium improves film music generation over text-only baselines.

  5. SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

    cs.SD 2025-06 conditional novelty 6.0 of 10

    SSLAM pre-trains audio transformers on partially mixed audio clips with a source retention loss, improving polyphonic sound tagging while keeping monophonic benchmark scores.

  6. SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet

    cs.SD 2025-05 conditional novelty 6.0 of 10

    A ControlNet branch plus a frequency-aware feature aligner lets a pretrained masked generative TTA model produce video-synchronized foley, beating several from-scratch models on VGGSound.

  7. FdAudio: MeanFlow-Anchored Fr\'echet-Distance Post-Training for One-Step Text-to-Audio Generation

    eess.AS 2026-07 conditional novelty 5.5 of 10

    MeanFlow-anchored multi-representation FD post-training improves one-step text-to-audio quality without collapsing multi-step sampling.

  8. JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing

    cs.CV 2025-12 conditional novelty 5.0 of 10

    A dual-branch diffusion transformer with joint video-audio self-attention and a keypoint-based mouth-area loss reports top lip-sync and speech metrics on two benchmarks.

  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. Adaptive Knowledge Distillation using a Device-Aware Teacher for Low-Complexity Acoustic Scene Classification

    cs.SD 2025-09 conditional novelty 4.0 of 10

    A low-complexity scene classifier trained by two-teacher knowledge distillation and device-specific fine-tuning reaches 57.93% accuracy on the DCASE 2025 development set.

  11. Joint Feature and Output Distillation for Low-complexity Acoustic Scene Classification

    cs.SD 2025-07 conditional novelty 4.0 of 10

    A 61k-parameter acoustic scene classifier trained with joint output-level and feature-level knowledge distillation reaches 59.30% accuracy on TAU Urban Acoustic Scenes 2022 Mobile.

  12. Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet

    eess.AS 2025-07 conditional novelty 4.0 of 10

    Replacing the Conformer decoder in pretrained PSELDnet with a bidirectional Mamba plus asymmetric convolution reports 39.6% versus 38.2% stereo SELD F20 on the DCASE2025 development set, using 76M versus 210M parameters.

  13. ASAudio: A Survey of Advanced Spatial Audio Research

    eess.AS 2025-08 unverdicted novelty 3.0 of 10

    A comprehensive survey that systematically categorizes spatial audio research by representation, task, dataset, and evaluation.

Pith tools