Audio signal processing by neural networks

Abstract In this paper a review of architectures suitable for nonlinear real-time audio signal processing is presented. The computational and structural complexity of neural networks (NNs) represent in fact, the main drawbacks that can hinder many practical NNs multimedia applications. In particular efficient neural architectures and their learning algorithm for real-time on-line audio processing are discussed. Moreover, applications in the fields of (1) audio signal recovery, (2) speech quality enhancement, (3) nonlinear transducer linearization, (4) learning based pseudo-physical sound synthesis, are briefly presented and discussed.

[1]  Truong Q. Nguyen.  Near-perfect-reconstruction pseudo-QMF banks , 1994, IEEE Trans. Signal Process..

[2]  Gonzalo R. Arce,et al.  A general class of nonlinear normalized adaptive filtering algorithms , 1999, IEEE Trans. Signal Process..

[3]  Hong Chen,et al.  Approximations of continuous functionals by neural networks with application to dynamic systems , 1993, IEEE Trans. Neural Networks.

[4]  Simon J. Godsill,et al.  Digital audio restoration , 1998 .

[5]  Martin Vetterli,et al.  Adaptive filtering in subbands with critical sampling: analysis, experiments, and application to acoustic echo cancellation , 1992, IEEE Trans. Signal Process..

[6]  Wolfgang Klippel,et al.  Nonlinear Large-Signal Behavior of Electrodynamic Loudspeakers at Low Frequencies , 1992 .

[7]  R. R. Leighton,et al.  The autoregressive backpropagation algorithm , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[8]  Carlo Drioli,et al.  Learning pseudo-physical models for sound synthesis and transformation , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[9]  Francesco Piazza,et al.  Multilayer feedforward networks with adaptive spline activation function , 1999, IEEE Trans. Neural Networks.

[10]  S. V. Vaseghi,et al.  Restoration of Old Gramophone Recordings , 1992 .

[11]  Francesco Piazza,et al.  Frequency recovery of narrow-band speech using adaptive spline neural networks , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[12]  Hikmet Sari,et al.  A data predistortion technique with memory for QAM radio systems , 1991, IEEE Trans. Commun..

[13]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[14]  N. Benvenuto,et al.  A neural network approach to data predistortion with memory in digital radio systems , 1993, Proceedings of ICC '93 - IEEE International Conference on Communications.

[15]  A. Uncini,et al.  Power-of-two adaptive filters using tabu search , 2000 .

[16]  Nam Ik Cho,et al.  On the performance analysis and applications of the subband adaptive digital filter , 1995, Signal Process..

[17]  A. Kaizer.  Modeling of the nonlinear response of an electrodynamic loudspeaker by a Volterra series expansion , 1987 .

[18]  Jenq-Neng Hwang,et al.  Neural networks for intelligent multimedia processing , 1997 .

[19]  Julius O. Smith,et al.  Physical Modeling Using Digital Waveguides , 1992 .

[20]  Michael C. Mozer,et al.  A Focused Backpropagation Algorithm for Temporal Pattern Recognition , 1989, Complex Syst..

[21]  N. Fletcher,et al.  Music Producers.(Book Reviews: The Physics of Musical Instruments.) , 1991 .

[22]  Hiroshi Yasukawa.  Signal restoration of broad band speech using nonlinear processing , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[23]  Paolo Campolucci,et al.  A Signal-Flow-Graph Approach to On-line Gradient Calculation , 2000, Neural Computation.

[24]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[25]  Fred W. Glover,et al.  Tabu Search , 1997, Handbook of Heuristics.

[26]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[27]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[28]  S. Vaseghi.  Detection and suppression of impulsive noise in speech communication systems , 1990 .

[29]  Jürgen Schmidhuber,et al.  Learning Complex, Extended Sequences Using the Principle of History Compression , 1992, Neural Computation.

[30]  Silvia De Fina,et al.  A new predistortion technique using neural nets , 1993, Signal Process..

[31]  Jose C. Principe,et al.  Prediction of Chaotic Time Series with Neural Networks , 1992 .

[32]  M. Schetzen,et al.  Nonlinear system modeling based on the Wiener theory , 1981, Proceedings of the IEEE.

[33]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[34]  Andrzej Czyzewski.  Artificial Intelligence-Based Processing of Old Audio Recordings , 1994 .

[35]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[36]  Hong Chen,et al.  Approximation capability in C(R¯n) by multilayer feedforward networks and related problems , 1995, IEEE Trans. Neural Networks.

[37]  Aurelio Uncini,et al.  An adaptive spline non-linear function for blind signal processing , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[38]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[39]  Jenq-Neng Hwang,et al.  Neural networks for intelligent multimedia processing , 1998 .

[40]  Francesco Piazza,et al.  Learning and Approximation Capabilities of Adaptive Spline Activation Function Neural Networks , 1998, Neural Networks.

[41]  Simon Haykin,et al.  Neural networks expand SP's horizons , 1996, IEEE Signal Process. Mag..

[42]  M. Gori,et al.  BPS: a learning algorithm for capturing the dynamic nature of speech , 1989, International 1989 Joint Conference on Neural Networks.

[43]  Wolfgang Klippel,et al.  Dynamic Measurement and Interpretation of the Nonlinear Parameters of Electrodynamic Loudspeakers , 1990 .

[44]  Ah Chung Tsoi,et al.  FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling , 1991, Neural Computation.

[45]  G. V. Puskorius,et al.  A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification , 1998, Proc. IEEE.

[46]  P. Regalia.  Adaptive IIR Filtering in Signal Processing and Control , 1994 .

[47]  Hikmet Sari,et al.  Analysis of predistortion, equalization, and ISI cancellation techniques in digital radio systems with nonlinear transmit amplifiers , 1989, IEEE Trans. Commun..

[48]  Sanjit K. Mitra,et al.  Performance analysis of adaptive filter structures based on subband decomposition , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[49]  Aurelio Uncini,et al.  Artificial neural networks with adaptive multidimensional spline activation functions , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[50]  S. Biyiksiz,et al.  Multirate digital signal processing , 1985, Proceedings of the IEEE.

[51]  Kumpati S. Narendra,et al.  Neural Networks In Dynamical Systems , 1990, Other Conferences.

[52]  José Carlos Príncipe,et al.  The gamma model--A new neural model for temporal processing , 1992, Neural Networks.

[53]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[54]  Michael Unser,et al.  Splines: a perfect fit for signal and image processing , 1999, IEEE Signal Process. Mag..

[55]  Hussein Baher,et al.  Analog & digital signal processing , 1990 .

[56]  Aurelio Uncini,et al.  Subband neural networks prediction for on-line audio signal recovery , 2002, IEEE Trans. Neural Networks.

[57]  Paolo Campolucci,et al.  Complex-valued neural networks with adaptive spline activation function for digital-radio-links nonlinear equalization , 1999, IEEE Trans. Signal Process..

[58]  Denis Baggi,et al.  Readings in computer-generated music , 1992 .

[59]  N. J. Fliege,et al.  Multirate Digital Signal Processing: Multirate Systems, Filter Banks, Wavelets , 1994 .

[60]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[61]  V. J. Mathews,et al.  Polynomial Signal Processing , 2000 .

[62]  Eric A. Wan,et al.  Temporal backpropagation for FIR neural networks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[63]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[64]  Saeed Vaseghi.  Advanced Signal Processing and Digital Noise Reduction , 1996 .

[65]  Robert C. Maher,et al.  A Method for Extrapolation of Missing Digital Audio Data , 1994 .

[66]  Bhaskar D. Rao,et al.  On-line learning algorithms for locally recurrent neural networks , 1999, IEEE Trans. Neural Networks.

[67]  Gary P. Scavone,et al.  An Acoustic Analysis Of Single-Reed Woodwind Instruments With An Emphasis On Design And Performance Issues And Digital Waveguide Modeling Techniques , 1997 .

[68]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[69]  A..  Temporal Backpropagation for FIR Neural Networks , 2004 .

[70]  Jing Peng,et al.  An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories , 1990, Neural Computation.

[71]  E. Catmull,et al.  A CLASS OF LOCAL INTERPOLATING SPLINES , 1974 .

[72]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[73]  Simon Haykin,et al.  Adaptive Filter Theory 4th Edition , 2002 .

[74]  Shun-ichi Amari,et al.  A universal theorem on learning curves , 1993, Neural Networks.