paper-with-me

홈 › Papers

Resource-Efficient Separation Transformer

2022-06-19 · Luca Della Libera, Cem Subakan, Mirco Ravanelli, Samuele Cornell, Frédéric Lepoutre, François Grondin

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameters. This paper explores Transformer-based speech separation with a reduced computational cost. Our main contribution is the development of the Resource-Efficient Separation Transformer (RE-SepFormer), a self-attention-based architecture that reduces the computational burden in two ways. First, it uses non-overlapping blocks in the latent space. Second, it operates on compact latent summaries calculated from each chunk. The RE-SepFormer reaches a competitive performance on the popular WSJ0-2Mix and WHAM! datasets in both causal and non-causal settings. Remarkably, it scales significantly better than the previous Transformer-based architectures in terms of memory and inference time, making it more suitable for processing long mixtures.

📄 PDF Abstract BibTeX arXiv:2206.09507

Code (1)

speechbrain/speechbrain 공식 구현 pytorch

Tasks

Speech Separation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Papez: Resource-Efficient Speech Separation with Auditory Working Memory

2024-07-01 · Hyunseok Oh, Juheon Yi, Youngki Lee

Transformer-based models recently reached state-of-the-art single-channel speech separation accuracy; However, their extreme computational load makes it difficult to deploy them in resource-constrained mobile or IoT devi…

Speech Separation

SPMamba: State-space model is all you need in speech separation

2024-04-02 · Kai Li, Guo Chen, Runxuan Yang, Xiaolin Hu

Existing CNN-based speech separation models face local receptive field limitations and cannot effectively capture long time dependencies. Although LSTM and Transformer-based speech separation models can avoid this proble…

AllMambaSpeech Separation

Ultra Fast Speech Separation Model with Teacher Student Learning

2022-04-27 · Sanyuan Chen, Yu Wu, Zhuo Chen, Jian Wu 외

Transformer has been successfully applied to speech separation recently with its strong long-dependency modeling capacity using a self-attention mechanism. However, Transformer tends to have heavy run-time costs due to t…

Computational EfficiencySpeech Separation

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers

2021-02-05 · Chaoyang He, Shen Li, Mahdi Soltanolkotabi, Salman Avestimehr

The size of Transformer models is growing at an unprecedented pace. It has only taken less than one year to reach trillion-level parameters after the release of GPT-3 (175B). Training such models requires both substantia…

Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning

2023-03-07 · Zhaoxi Mu, Xinyu Yang, Wenjing Zhu

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation i…

Speech Separation