PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network

Authors: Dacheng Yin, Chong Luo, Zhiwei Xiong, Wenjun Zeng9458-9465

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We carry out comprehensive experiments to justify the design choices and to demonstrate the performance superiority of PHASEN over existing noise reduction methods.
Researcher Affiliation Collaboration 1University of Science and Technology of China 2Microsoft Research Asia
Pseudocode No The paper describes the architecture and operations in text and diagrams (Fig. 2, Fig. 3), but does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper mentions 'the released code' for Conv-Tas Net, a baseline method, but does not provide concrete access to the source code for PHASEN, nor does it state that PHASEN's code is open source or available.
Open Datasets Yes AVSpeech+Audio Set: This is a large dataset proposed by (Ephrat et al. 2018). Clean speech dataset AVSpeech is collected from You Tube... Noise dataset Audio Set (Gemmeke et al. 2017)... Voice Bank+DEMAND: This is an open dataset1 proposed by (Valentini-Botinhao et al. 2016). Speech of 30 speakers from the Voice Bank corpus (Ephrat et al. 2018)... The noisy speech is synthesized using a mixture of clean speech with noise from Diverse Environments Multichannel Acoustic Noise Database (DEMAND) (Thiemann, Ito, and Vincent 2013).
Dataset Splits Yes In our experiments, 100k segments randomly sampled from AVSpeech dataset and the Balanced Train part of Audio Set are used to synthesize the training set, while the validation set is the same as the one used in (Ephrat et al. 2018), synthesized by the test part of AVSpeech dataset and the evaluation part of Audio Set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments.
Software Dependencies No The paper states 'PHASEN is implemented in Pytorch' but does not specify the version of PyTorch or any other software dependencies with their respective version numbers.
Experiment Setup Yes Adam optimizer with a fixed learning rate of 0.0002 is used and the batch size is set to 8.