Audiodec: An open-source streaming high-fidelity neural audio codec
A good audio codec for live applications such as telecommunication is characterized by
three key properties:(1) compression, ie the bitrate that is required to transmit the signal …
three key properties:(1) compression, ie the bitrate that is required to transmit the signal …
Nonlinear analysis of speech from a synthesis perspective
M Banbrook - 1996 - era.ed.ac.uk
With the emergence of nonlinear dynamical systems analysis over recent years it has
become clear that conventional time domain and frequency domain approaches to speech …
become clear that conventional time domain and frequency domain approaches to speech …
[PDF][PDF] Nonlinear speech processing: overview and applications
M Faundez-Zanuy, S McLaughlin… - Control and intelligent …, 2002 - academia.edu
This article presents an overview of various nonlinear processing techniques applied to
speech signals. Eevidence relating to the existence of nonlinearities in speech is presented …
speech signals. Eevidence relating to the existence of nonlinearities in speech is presented …
End-to-end optimized speech coding with deep neural networks
S Kankanahalli - … Conference on Acoustics, Speech and Signal …, 2018 - ieeexplore.ieee.org
Modern compression algorithms are often the result of laborious domain-specific research;
industry standards such as MP3, JPEG, and AMR-WB took years to develop and were …
industry standards such as MP3, JPEG, and AMR-WB took years to develop and were …
Memory-universal prediction of stationary random processes
DS Modha, E Masry - IEEE transactions on information theory, 1998 - ieeexplore.ieee.org
We consider the problem of one-step-ahead prediction of a real-valued, stationary, strongly
mixing random process (Xi)/sub i=-/spl infin///sup/spl infin//. The best mean-square predictor …
mixing random process (Xi)/sub i=-/spl infin///sup/spl infin//. The best mean-square predictor …
Composition of deep and spiking neural networks for very low bit rate speech coding
Most current very low bit rate (VLBR) speech coding systems use hidden Markov model
(HMM) based speech recognition and synthesis techniques. This allows transmission of …
(HMM) based speech recognition and synthesis techniques. This allows transmission of …
Testing the assumptions of linear prediction analysis in normal vowels
In this paper we develop an improved surrogate data test to show experimental evidence, for
all the simple vowels of US English, for both male and female speakers, that Gaussian linear …
all the simple vowels of US English, for both male and female speakers, that Gaussian linear …
A fully Kalman-trained radial basis function network for nonlinear speech modeling
M Birgmeier - Proceedings of ICNN'95-International Conference …, 1995 - ieeexplore.ieee.org
This paper presents a radial basis function neural network which is trained to learn the
dynamics of nonlinear autonomous systems. Contrary to conventional approaches, not only …
dynamics of nonlinear autonomous systems. Contrary to conventional approaches, not only …
Set membership prediction of nonlinear time series
M Milanese, C Novara - IEEE Transactions on Automatic …, 2005 - ieeexplore.ieee.org
In this paper, a prediction method for nonlinear time series based on a set membership (SM)
approach is proposed. The method does not require the choice of the functional form of the …
approach is proposed. The method does not require the choice of the functional form of the …
[PDF][PDF] Speech processing with linear and neural network models
TL Burrows - 1996 - Citeseer
This dissertation investigates some aspects of speech processing using linear models and
single hidden layer neural networks. The study is divided into two parts which focus on …
single hidden layer neural networks. The study is divided into two parts which focus on …