An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec

no code implementations • 2 Feb 2024 • Linping Xu, Jiawei Jiang, Dejun Zhang, Xianjun Xia, Li Chen, Yijian Xiao, Piao Ding, Shenyi Song, Sixing Yin, Ferdous Sohel

Recently, neural networks have proven to be effective in performing speech coding task at low bitrates.

Quantization

Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model

no code implementations • 7 Apr 2022 • Nick J. C. Wang, Lu Wang, Yandan Sun, Haimei Kang, Dejun Zhang

We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information

no code implementations • 31 Mar 2021 • Linchao He, Mengting Luo, Dejun Zhang, Xiao Yang, Hu Chen, Yi Zhang

In this paper, we introduce the homotopy equivalence relation (HER) to make the neural networks learn the data distribution from a high-dimension manifold.

Contrastive Learning Point Cloud Classification