Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks
By Yuichiro Koyama, Tyler Vuong, Stefan Uhlich, Bhiksha Raj. 2020
48 citations recorded by the source corpus.
Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform (STFT) has been widely used for DNN-based speech enhancement over the last years, time domain methods such as the time-domain audio separation network (TasNet) have also been proposed. The most suitable method depends on the scale of the dataset and the type of task. In this paper, we explore the best speech enhancement algorithm on two different datasets. We propose a STFT-based method and a loss function using problem-agnostic speech encoder (PASE) features to improve subjective quality for the smaller dataset. Our proposed methods are effective on the Voice Bank + DEMAND dataset and compare favorably to other state-of-the-art methods. We also implement a low-latency version of TasNet, which we submitted to the DNS Challenge and made public by open-sourcing it. Our model achieves excellent performance on the DNS Challenge dataset.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ross Cutler
- Vishak Gopal
- Sebastian Braun
- Chandan K. A. Reddy
- Robert Aichner
- Harishchandra Dubey
- Xiulian Peng
- Yan Lu
In Signal Processing
- Ross Cutler
- Vishak Gopal
- Chandan K. A. Reddy
- Robert Aichner
- Hannes Gamper
- Sebastian Braun
- Harishchandra Dubey
- Sriram Srinivasan
Citations in the corpus
- Icassp 2022 Deep Noise Suppression Challenge (2022, background): “In recent years, deep learning based approaches have shown promising results for superior speech quality [2, 3, 4].”
- Interspeech 2021 Deep Noise Suppression Challenge (2021, background): “In recent years, learning-based approaches have shown promising results [3, 4, 5].”
- Interactive Speech and Noise Modeling for Speech Enhancement (2020, methodology): “Conv-TasNet-SNR (Koyama et al. 2020) and DTLN (WestMethods SDRi(dB) PESQ2”
- Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement (2020, methodology): “[24] proposed a low-latency Conv-TasNet.”
- ICASSP 2021 Deep Noise Suppression Challenge (2020, background): “In recent years, learning-based approaches have shown promising results [3, 4, 5].”