MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions

• URL: http://arxiv.org/abs/2302.11824v1
• Date: Thu, 23 Feb 2023 07:17:12 GMT
• Title: MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
• Abstract summary: We propose a single-head gated transformer architecture with convolution-augmented joint self-attentions, named textitMossFormer. MossFormer significantly outperforms the previous models and achieves the state-of-the-art results on WSJ0-2/3mix and WHAM!/WHAMR! benchmarks.
• Score: 26.862052778354016
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed upper bound. The major limitation of the current dual-path Transformer models is the inefficient modelling of long-range elemental interactions and local feature patterns. In this work, we achieve the upper bound by proposing a gated single-head transformer architecture with convolution-augmented joint self-attentions, named \textit{MossFormer} (\textit{Mo}naural \textit{s}peech \textit{s}eparation Trans\textit{Former}). To effectively solve the indirect elemental interactions across chunks in the dual-path architecture, MossFormer employs a joint local and global self-attention architecture that simultaneously performs a full-computation self-attention on local chunks and a linearised low-cost self-attention over the full sequence. The joint attention enables MossFormer model full-sequence elemental interaction directly. In addition, we employ a powerful attentive gating mechanism with simplified single-head self-attentions. Besides the attentive long-range modelling, we also augment MossFormer with convolutions for the position-wise local pattern modelling. As a consequence, MossFormer significantly outperforms the previous models and achieves the state-of-the-art results on WSJ0-2/3mix and WHAM!/WHAMR! benchmarks. Our model achieves the SI-SDRi upper bound of 21.2 dB on WSJ0-3mix and only 0.3 dB below the upper bound of 23.1 dB on WSJ0-2mix.

Related papers

• Solve the Loop: Attractor Models for Language and Reasoning [4.8720589853137435]
  Looped Transformers offer a promising alternative to purely feed-forward computation.<n>We introduce Attractor Models, in which a backbone module first proposes output embeddings, then an attractor module refines them by solving for the fixed point.<n>We show that Attractor Models outperform existing models across two regimes, large-scale language-model pretraining and reasoning with tiny models.
  arXiv  Detail & Related papers  (2026-05-12T17:51:26Z)
• HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents [71.09493646932046]
  We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents.<n>The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning.<n>Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro.
  arXiv  Detail & Related papers  (2026-04-08T17:59:48Z)
• Mamba-3: Improved Sequence Modeling using State Space Principles [74.41028882099846]
  We introduce three core methodological improvements inspired by the state space model (SSM) viewpoint of linear models.<n>Together with architectural refinements, our Mamba-3 model achieves significant gains across retrieval, state-tracking, and downstream language modeling tasks.
  arXiv  Detail & Related papers  (2026-03-16T17:30:08Z)
• A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning [57.727084580884075]
  Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
  arXiv  Detail & Related papers  (2025-09-26T08:27:03Z)
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free [81.65559031466452]
  We conduct experiments to investigate gating-augmented softmax attention variants.<n>We find that a simple modification-applying a head-specific sigmoid gate after the Scaled Dot-Product Attention (SDPA)-consistently improves performance.
  arXiv  Detail & Related papers  (2025-05-10T17:15:49Z)
• ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration [61.579842548990754]
  Mixture-of-Experts (MoE) Transformer, the backbone of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for each input token. We introduce ResMoE, an innovative MoE approximation framework that utilizes Wasserstein barycenter to extract a common expert (barycenter expert) and approximate the residuals between this barycenter expert and the original ones.
  arXiv  Detail & Related papers  (2025-03-10T03:15:54Z)
• FuXi-$α$: Scaling Recommendation Model with Feature Interaction Enhanced Transformer [81.12174905444229]
  Recent advancements have shown that expanding sequential recommendation models to large-scale recommendation models can be an effective strategy. We propose a new model called FuXi-$alpha$ to address these issues. Our model outperforms existing models, with its performance continuously improving as the model size increases.
  arXiv  Detail & Related papers  (2025-02-05T09:46:54Z)
• DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 [6.6954598568836925]
  DiM-Gestor is an end-to-end generative model leveraging the Mamba-2 architecture. A fuzzy feature extractor and a speech-to-gesture mapping module are built on the Mamba-2. Our approach delivers competitive results and significantly reduces memory usage, approximately 2.4 times, and enhances inference speeds by 2 to 4 times.
  arXiv  Detail & Related papers  (2024-11-23T08:02:03Z)
• ConvMixFormer- A Resource-efficient Convolution Mixer for Transformer-based Dynamic Hand Gesture Recognition [5.311735227179715]
  We explore and devise a novel ConvMixFormer architecture for dynamic hand gestures. The proposed method is evaluated on NVidia Dynamic Hand Gesture and Briareo datasets. Our model has achieved state-of-the-art results on single and multimodal inputs.
  arXiv  Detail & Related papers  (2024-11-11T16:45:18Z)
• CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications [73.80247057590519]
  Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. We introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications. Our model achieves 83.0%/84.1% top-1 with only 12M/21M parameters on ImageNet-1K.
  arXiv  Detail & Related papers  (2024-08-07T11:33:46Z)
• DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 framework [2.187990941788468]
  generative model crafted to create highly personalized 3D full-body gestures solely from raw speech audio. Model integrates a Mamba-based fuzzy feature extractor with a non-autoregressive Adaptive Layer Normalization (AdaLN) Mamba-2 diffusion architecture.
  arXiv  Detail & Related papers  (2024-08-01T08:22:47Z)
• Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules [96.21649779507831]
  We propose a novel architecture dubbed mixture-of-modules (MoM) MoM is motivated by an intuition that any layer, regardless of its position, can be used to compute a token. We show that MoM provides not only a unified framework for Transformers but also a flexible and learnable approach for reducing redundancy.
  arXiv  Detail & Related papers  (2024-07-09T08:50:18Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion [54.33764537135906]
  VideoQA Transformer models demonstrate competitive performance on standard benchmarks. Do these models capture the rich multimodal structures and dynamics from video and text jointly? Are they achieving high scores by exploiting biases and spurious features?
  arXiv  Detail & Related papers  (2023-06-15T06:45:46Z)
• STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition [50.064502884594376]
  We study the problem of human action recognition using motion capture (MoCap) sequences. We propose a novel Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh sequences. The proposed method achieves state-of-the-art performance compared to skeleton-based and point-cloud-based models.
  arXiv  Detail & Related papers  (2023-03-31T16:19:27Z)
• Squeezeformer: An Efficient Transformer for Automatic Speech Recognition [99.349598600887]
  Conformer is the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture. We propose the Squeezeformer model, which consistently outperforms the state-of-the-art ASR models under the same training schemes.
  arXiv  Detail & Related papers  (2022-06-02T06:06:29Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)
• Scaling Local Self-Attention For Parameter Efficient Visual Backbones [29.396052798583234]
  Self-attention has the promise of improving computer vision systems due to parameter-independent scaling of receptive fields and content-dependent interactions. We develop a new self-attention model family, emphHaloNets, which reach state-of-the-art accuracies on the parameter-limited setting of the ImageNet classification benchmark.
  arXiv  Detail & Related papers  (2021-03-23T17:56:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.