paper-with-me

Papers

Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model

2023-06-01 · Xiaohuai Le, Tong Lei, Li Chen, Yiqing Guo, Chao He, Cheng Chen, Xianjun Xia, Hua Gao, Yijian Xiao, Piao Ding, Shenyi Song, Jing Lu

With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccurate fundamental frequency estimation. To tackle this problem, we propose a learnable comb filter to enhance harmonics. Based on the sub-band model, we design a DNN-based fundamental frequency estimator to estimate the discrete fundamental frequencies and a comb filter for harmonic enhancement, which are trained via an end-to-end pattern. The experiments show the advantages of our proposed method over PecepNet and DeepFilterNet.

📄 PDF Abstract BibTeX arXiv:2306.00812

Code (0)

등록된 구현이 없습니다.

Tasks

RetrievalSpeech Enhancement

Similar Papers 제목 키워드 기반

HGCN: Harmonic gated compensation network for speech enhancement

2022-01-30 · Tianrui Wang, Weibin Zhu, Yingying Gao, Junlan Feng 외

Mask processing in the time-frequency (T-F) domain through the neural network has been one of the mainstreams for single-channel speech enhancement. However, it is hard for most models to handle the situation when harmon…

Action DetectionActivity DetectionSpeech Enhancement

Harmonic Detection from Noisy Speech with Auditory Frame Gain for Intelligibility Enhancement

2024-01-22 · A. Queiroz, R. Coelho

This paper introduces a novel (HDAG - Harmonic Detection for Auditory Gain) method for speech intelligibility enhancement in noisy scenarios. In the proposed scheme, a series of selective Gammachirp filters are adopted t…

Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Module

2024-01-12 · Seitaro Ono, Yuka Ogino, Takahiro Toizumi, Atsushi Ito 외

In recent years, significant progress has been made in image recognition technology based on deep neural networks. However, improving recognition performance under low-light conditions remains a significant challenge. Th…

DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio

2022-05-11 · Hendrik Schröter, Alberto N. Escalante-B., Tobias Rosenkranz, Andreas Maier

Deep learning-based speech enhancement has seen huge improvements and recently also expanded to full band audio (48 kHz). However, many approaches have a rather high computational complexity and require big temporal buff…

CPUData AugmentationSpeech Enhancement

Harmonic Convolutional Networks based on Discrete Cosine Transform

2020-01-18 · Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spectral filters defined by the Discrete Cos…

Edge Detectionimage-classificationImage Classificationobject-detection+2