ADPCM with nonlinear prediction

Many speech coders are based on linear prediction coding (LPC), nevertheless with LPC is not possible to model the nonlinearities present in the speech signal. Because of this there is a growing interest for nonlinear techniques. In this paper we discuss ADPCM schemes with a nonlinear predictor based on neural nets, which yields an increase of 1-2.5dB in the SEGSNR over classical methods. This paper will discuss the block-adaptive and sample-adaptive predictions.

eess.AS cs.LG Neural Networks and Applications Advanced Data Compression Techniques Image and Signal Denoising Methods

Paper

Similar papers

Speaker-dependent Wavenet-based Delay-free Adpcm Speech CodingTakenori Yoshimura, Kei Hashimoto, Keiichiro Oura et al.2019 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 7 citations In Library

Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech CodingHaici Yang, Wootaek Lım, Minje Kim2023 In Library

An Efficient Subband Linear Prediction for LPCNet-Based Neural SynthesisYang Cui, Xi Wang, Lei He et al.2020 · Interspeech · 10 citations In Library

Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech CodingHaici Yang, Wootaek Lım, Minje Kim2022 · arXiv (Cornell University) · 9 citations In Library

An Adaptive Algorithm for Sequential Adaptive Predictive Coding of Speed Signals.(Dept.E)Fayez Soliman, Rasheed El-Awady2021 · MEJ Mansoura Engineering Journal In Library

A New Nonlinear speaker parameterization algorithm for speaker identificationMohamed Chétouani, Marcos Faúndez-Zanuy, Bruno Gas et al.2022 · arXiv (Cornell University) In Library

Speaker recognition by means of a combination of linear and nonlinear predictive modelsMarcos Faúndez-Zanuy2022 · arXiv (Cornell University) · 7 citations In Library

LPCNet: Improving Neural Speech Synthesis Through Linear PredictionJ. Valin, J. Skoglund2018 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 500 citations In Library

Speech Prediction Using an Adaptive Recurrent Neural Network with Application to Packet Loss ConcealmentReza Lotfidereshgi, P. Gournay2018 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 41 citations In Library

Single and multiple frame coding of LSF parameters using deep neural network and pyramid vector quantizerYaxing Li, Ying Kang, Hao Wu et al.2020 · Speech Communication · 2 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal