Root homomorphic deconvolution schemes for speech processing in car noise environments
IEEE International Conference on Acoustics Speech and Signal ProcessingPublished 1 January 1993
Patrice Alexandre, J. Boudy, P. Lockwood
Citations13
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The authors propose the use of a Root homomorphic approach instead of the classical Log in order to improve cepstral representation in noise and demonstrate the robustness of the Root-based analysis for noisy speech processing.
Abstract
The authors propose the use of a Root homomorphic approach instead of the classical Log in order to improve cepstral representation in noise. Recognition tests demonstrate the robustness of the Root-based analysis for noisy speech processing. It is shown that Root cepstral coefficients permit a heuristic extension of noise subtraction techniques into the cepstral domain. Finally, the authors extend their work to LP (linear prediction)-based cepstral analysis and show that the Root approach gives equivalent results when comparing direct (LFCC) and LP-based (LPCC) analysis schemes. A unified model is proposed, and it is concluded that both classical LPCC and LFCC analyses are suboptimal solutions of the authors' more general scheme.>
Keywords
Computer ScienceEngineering
IEEE Transactions on Acoustics Speech and Signal ProcessingComparison of parametric representations for monosyllabic word recognition in continuously spoken sentences
5,322 Citations1980S. Davis, P. Mermelstein
Several parametric representations of the acoustic signal were compared with regard to word recognition performance in a syllable-oriented continuous speech recognition system and the superior performance of the mel-frequency cepstrum coefficients may be attributed to the fact that they better represent the perceptually relevant aspects of the short-term speech spectrum.
Proceedings of the IEEELinear prediction: A tutorial review
3,996 Citations1975J. Makhoul
This paper gives an exposition of linear prediction in the analysis of discrete signals as a linear combination of its past values and present and past values of a hypothetical input to a system whose output is the given signal.
IEEE Transactions on Acoustics Speech and Signal ProcessingSpeaker-independent isolated word recognition using dynamic features of speech spectrum
741 Citations1986Sadaoki Furui
This paper proposes a new isolated word recognition technique based on a combination of instantaneous and dynamic features of the speech spectrum that is shown to be highly effective in speaker-independent speech recognition.
Proceedings of the IEEENonlinear filtering of multiplied and convolved signals
502 Citations1968Alan V. Oppenheim, Ronald W. Schafer +1 more
The applications of this approach in audio dynamic range compression and expansion, image enhancement with applications to bandwidth reduction, echo removal, and speech waveform processing are presented.
Speech CommunicationExperiments with a nonlinear spectral subtractor (NSS), Hidden Markov models and the projection, for robust speech recognition in cars
348 Citations1992P. Lockwood, J. Boudy
The performance of an HMM-based recogniser rises from 56% (no compensation) to 98% after speech enhancement and the lower limit of applicability of the projection (low SNR values) can be loosened after combination with NSS.
IEEE Transactions on Audio and ElectroacousticsNonlinear filtering of multiplied and convolved signals
282 Citations1968Alan V. Oppenheim, Ronald W. Schafer +1 more
RASTA-PLP speech analysis technique
259 Citations1992Hynek Heřmanský, N. Morgan +2 more
The authors have developed a technique that is more robust to such steady-state spectral factors in speech that is conceptually simple and computationally efficient.
An improved approach to the hidden Markov model decomposition of speech and noise
156 Citations1992Mark Gales, S.J. Young
The author addresses the problem of automatic speech recognition in the presence of interfering noise by decomposing the contaminated speech signal using a generalization of standard hidden Markov modeling, while utilizing a compact and effective parametrization of the speech signal.
IEEE Transactions on Acoustics Speech and Signal ProcessingThe short-time modified coherence representation and noisy speech recognition
109 Citations1989D. Mansour, B.-H. Juang
Initial implementation of the SMC in a speaker-dependent isolated word recognizer shows an improvement in recognition accuracy equivalent to an increase in input SNR of approximately 13 dB, as compared to the LPC recognizer.
IEEE Transactions on Acoustics Speech and Signal ProcessingSpectral root homomorphic deconvolution system
83 Citations1979Jae S. Lim
Speech CommunicationRoot cepstral analysis: A unified view. Application to speech processing in car noise environments
75 Citations1993Patrice Alexandre, P. Lockwood
A pseudo-autocorrelation domain is introduced, which can be interpreted as a “Root-cepstral domain”, and it is shown how non-parametric cepstral and linear predictive analyses converge to the same optimal solution.
Non-linear spectral subtraction (NSS) and hidden Markov models for robust speech recognition in car noise environments
53 Citations1992P. Lockwood, J. Boudy +1 more
The authors extend their previous work where a robust hidden Markov model (HMM) training/recognition framework is proposed and several new aspects are introduced: use of enhanced nonlinear spectral subtraction (NSS) schemes, introduction of root-MFCC parameters, and training of HMMs by a dynamic inference scheme (DIHMM).
IEEE Transactions on Acoustics Speech and Signal ProcessingSpectral analysis using generalized cepstrum
53 Citations1984Takao Kobayashi, Satoshi Imai
A natural generalization of theLogarithmic function is used instead of the logarithic function itself and the spectral representation parameter on the "generalized logarathmic" scale is referred to as the " generalized cepstrum," which corresponds to the cep strum on the logARithmic scale.
Fast self-adapting broadband noise removal in the cepstral domain
7 Citations1991Chang-Yi Wu, Nguyễn Văn Tảo +3 more
A fast self-adapting algorithm to remove broadband noise in the cepstral domain is presented and yields good speech quality with little spectral distortion in the fast-changing F-15/F-16 aircraft cockpit environment.