no code implementations • 13 Feb 2022 • Ruixue Lian, Che-Wei Huang, Yuqing Tang, Qilong Gu, Chengyuan Ma, Chenlei Guo
Individual user profiles and interaction histories play a significant role in providing customized experiences in real-world applications such as chatbots, social media, retail, and education.
no code implementations • 9 Mar 2021 • Samik Sadhu, Di He, Che-Wei Huang, Sri Harish Mallidi, Minhua Wu, Ariya Rastrow, Andreas Stolcke, Jasha Droppo, Roland Maas
However, the quantization process is regularized by an additional consistency network that learns to reconstruct the input features to the wav2vec 2. 0 network from the quantized representations in a way similar to a VQ-VAE model.
no code implementations • 27 Jul 2020 • Jinxi Guo, Gautam Tiwari, Jasha Droppo, Maarten Van Segbroeck, Che-Wei Huang, Andreas Stolcke, Roland Maas
Unlike previous work on this topic, which performs on-the-fly limited-size beam-search decoding and generates alignment scores for expected edit-distance computation, in our proposed method, we re-calculate and sum scores of all the possible alignments for each hypothesis in N-best lists.
no code implementations • 2 Aug 2018 • Che-Wei Huang, Shrikanth. S. Narayanan
Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples.
no code implementations • 7 Jun 2017 • Che-Wei Huang, Shrikanth. S. Narayanan
Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech.