Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2212.07163

Multi-Scale Feature Fusion Transformer Network for End-to-End Single Channel Speech Separation

Yinhao Xu·Jian Zhou·Liang Tao·Hon Keung Kwan
View original source ↗Read source document ↗Export metadata ↓

Abstract

Recently studies on time-domain audio separation networks (TasNets) have made a great stride in speech separation. One of the most representative TasNets is a network with a dual-path segmentation approach. However, the original model called DPRNN used a fixed feature dimension and unchanged segment size throughout all layers of the network. In this paper, we propose a multi-scale feature fusion transformer network (MSFFT-Net) based on the conventional dual-path structure for single-channel speech separation. Unlike the conventional dual-path structure where only one processing path exists, adopting several iterative blocks with alternative intra-chunk and inter-chunk operations to capture local and global context information, the proposed MSFFT-Net has multiple parallel processing paths where the feature information can be exchanged between multiple parallel processing paths. Experiments show that our proposed networks based on multi-scale feature fusion structure have achieved better results than the original dual-path model on the benchmark dataset-WSJ0-2mix, where the SI-SNRi score of MSFFT-3P is 20.7dB (1.47% improvement), and MSFFT-2P is 21.0dB (3.45% improvement), which achieves SOTA on WSJ0-2mix without any data augmentation method.

Explore related subjects

cs.SDeess.AS

Keep this discovery

BibTeXRIS

Yinhao Xu, Jian Zhou, Liang Tao, Hon Keung Kwan. 2022-12-14. Multi-Scale Feature Fusion Transformer Network for End-to-End Single Channel Speech Separation. https://arxiv.org/abs/2212.07163

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗