W
Wei Xiao
Researcher at Huawei
Publications - 8
Citations - 308
Wei Xiao is an academic researcher from Huawei. The author has contributed to research in topics: Mel-frequency cepstrum & Computer science. The author has an hindex of 4, co-authored 6 publications receiving 251 citations.
Papers
More filters
Journal ArticleDOI
Robust sound event classification using deep neural networks
TL;DR: A sound event classification framework is outlined that compares auditory image front end features with spectrogram image-based frontEnd features, using support vector machine and deep neural network classifiers, and is shown to compare very well with current state-of-the-art classification techniques.
Journal ArticleDOI
Continuous robust sound event classification using time-frequency features and deep learning
TL;DR: This paper proposes and evaluates a novel Bayesian-inspired front end for the segmentation and detection of continuous sound recordings prior to classification, and benchmarks several high performing isolated sound classifiers to operate with continuous sound data by incorporating an energy-based event detection front end.
Proceedings ArticleDOI
Multi-channel noise reduction for hands-free voice communication on mobile phones
TL;DR: Evaluation results on real-world recordings collected via a smartphone confirm its superior effectiveness to suppress the fast-varying noises compared to the state-of-the-art baseline methods.
Journal ArticleDOI
A new variance-based approach for discriminative feature extraction in machine hearing classification using spectrogram features
TL;DR: A novel data-driven feature extraction method that uses variance-based criteria to define spectral pooling of features from spectrograms is explored, and is shown to achieve very good performance for robust classification.
Proceedings ArticleDOI
ConferencingSpeech 2022 Challenge: Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge for Online Conferencing Applications
Gaoxiong Yi,Wei Xiao,Yiming Xiao,Babak Naderi,S. Moller,Wafaa Wardah,Gabriel Mittag,Ross Cutler,Zhuohuang Zhang,Donald S. Williamson,Fei Chen,Fuzheng Yang,Shidong Shang +12 more
TL;DR: The ConferencingSpeech 2022 challenge targets the non-intrusive deep neural network models for the speech quality assessment task and open-sourced a training corpus with more than 86K speech clips in different languages, with a wide range of synthesized and live degradations and their corresponding subjective quality scores.