paper-with-me

홈 › Papers

Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes

2022-06-23 · Danilo de Oliveira, Tal Peer, Timo Gerkmann

The SepFormer architecture shows very good results in speech separation. Like other learned-encoder models, it uses short frames, as they have been shown to obtain better performance in these cases. This results in a large number of frames at the input, which is problematic; since the SepFormer is transformer-based, its computational complexity drastically increases with longer sequences. In this paper, we employ the SepFormer in a speech enhancement task and show that by replacing the learned-encoder features with a magnitude short-time Fourier transform (STFT) representation, we can use long frames without compromising perceptual enhancement performance. We obtained equivalent quality and intelligibility evaluation scores while reducing the number of operations by a factor of approximately 8 for a 10-second utterance.

📄 PDF Abstract BibTeX arXiv:2206.11703

Code (0)

등록된 구현이 없습니다.

Tasks

Speech EnhancementSpeech Separation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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…
PReLU A Parametric Rectified Linear Unit, or PReLU, is an activation function that generalizes the traditional rectified unit with a slope for negative values.…
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 $x$…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Enhancement and Recognition of Reverberant and Noisy Speech by Extending Its Coherence

2015-09-02 · Scott Wisdom, Thomas Powers, Les Atlas, James Pitton

Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time spectrum of a signal. However, the duratio…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speech Enhancementspeech-recognition+1

Deep Multi-Frame MVDR Filtering for Single-Microphone Speech Enhancement

2020-11-20 · Marvin Tammen, Simon Doclo

Multi-frame algorithms for single-microphone speech enhancement, e.g., the multi-frame minimum variance distortionless response (MFMVDR) filter, are able to exploit speech correlation across adjacent time frames in the s…

Speech Enhancement

Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement

2023-06-15 · Liang Wan, Hongqing Liu, Yi Zhou, Jie Ji

The Dual-Path Convolution Recurrent Network (DPCRN) was proposed to effectively exploit time-frequency domain information. By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a prom…

Speech EnhancementSpeech Separation

A Two-Stage Framework in Cross-Spectrum Domain for Real-Time Speech Enhancement

2024-01-19 · Yuewei Zhang, Huanbin Zou, Jie Zhu

Two-stage pipeline is popular in speech enhancement tasks due to its superiority over traditional single-stage methods. The current two-stage approaches usually enhance the magnitude spectrum in the first stage, and furt…

Speech Enhancement

Efficient Trainable Front-Ends for Neural Speech Enhancement

2020-02-20 · Jonah Casebeer, Umut Isik, Shrikant Venkataramani, Arvindh Krishnaswamy

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literatu…

Speech Enhancement