End-to-end Speech Enhancement Based On Discrete Cosine Transform

Abstract

Previous speech enhancement methods focus on estimating the short-time spectrum of speech signals due to its short-term stability. However, these methods often only estimate the clean magnitude spectrum and reuse the noisy phase when resynthesize speech signals, which is unlikely a valid short-time Fourier transform (STFT). Recently, DNN based speech enhancement methods mainly joint estimation of the magnitude and phase spectrum. These methods usually give better performance than magnitude spectrum estimation but need much larger computation and memory overhead. In this paper, we propose using the Discrete Cosine Transform (DCT) to reconstruct a valid short-time spectrum. Under the U-net structure, we enhance the real spectrogram and finally achieve perfect performance.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keygeng2019end

Related papers

• Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform (2021)0.00
• Invertible Dnn-based Nonlinear Time-frequency Transform For Speech Enhancement (2019)7.16
• A Two-stage Framework In Cross-spectrum Domain For Real-time Speech Enhancement (2024)7.81
• A Dual-staged Context Aggregation Method Towards Efficient End-to-end Speech Enhancement (2019)0.00
• End-to-end Waveform Utterance Enhancement For Direct Evaluation Metrics Optimization By Fully Convolutional Neural Networks (2017)18.00
• Concatenated Identical DNN (CI-DNN) To Reduce Noise-type Dependence In Dnn-based Speech Enhancement (2018)5.24
• Trainable Adaptive Window Switching For Speech Enhancement (2018)6.77
• Improved Speech Enhancement With The Wave-u-net (2018)0.00