Modeling the temporal evolution of LPC parameters for codebook-based speech enhancement

Rosenkranz, Tobias

doi:10.1109/ispa.2009.5297763

Cited by 3 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Codebook based approaches [43][44][45][46][47] try to overcome this limitation by estimating the noise parameters based on a priori knowledge about different speech and noise types. In these approaches, joint estimation of the speech and noise PSD is performed on a frameby-frame basis by exploiting a priori information stored in the form of trained codebooks of short term prediction parameter vectors.…”

Section: Codebook Assisted Speech Enhancementmentioning

confidence: 99%

“…These codebooks are generated during a preliminary training stage that employs pre-selected speech and noise signal samples for the intended application. Examples of the short term parameters used in these codebooks are the gain normalized linear predictive (LP) coefficients [43][44][45][46] and the cepstral coefficients [47,48]. Specifically, the codebooks are trained by windowing a set of representative speech and noise signal samples into frames, obtaining the corresponding short term prediction parameter vector for each frame, and finally performing vector quantization on these vectors to obtain the final set of representative codebook vectors [49].…”

Section: Codebook Assisted Speech Enhancementmentioning

confidence: 99%

“…This estimation amounts to finding the best combination of gain variance and short term parameter vectors from the codebook for both speech and noise spectra, based on the observed noisy speech spectrum. Several approaches, including maximum likelihood, maximum a posteriori (MAP), MMSE and hidden Markov models (HMM) are available to tackle this issue, as proposed in, e.g., [43][44][45][46][47]. Once the speech and noise PSD have been properly estimated, they can be used to compute a gain function for the purpose of speech enhancement, as per previously described enhancement methods such as MMSE-STSA or Wiener filtering.…”

Section: Codebook Assisted Speech Enhancementmentioning

confidence: 99%

“…The use of these codebook methods in the acoustic AMS framework has shown promising results in the enhancement of speech corrupted by non-stationary noise [43][44][45][46][47]. However, to the best of our knowledge, they have not been applied yet to the modulation domain framework, where they could also bring similar benefits.…”

Section: Thesis Objective and Contributionmentioning

confidence: 99%

“…Frame-by-frame estimation of noise PSD makes it possible for this method to track quickly varying noise levels in a noisy speech signal in a satisfactory manner. Speech enhancement methods proposed over the years based on this estimation approach have been reported to perform reasonable enhancement under non-stationary background noise conditions [45][46][47].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Mani

Champagne

Zhu

2015

2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

Conventional single-channel speech enhancement methods implement the analysis-modification-synthesis (AMS) framework in the acoustic frequency domain. Recently, it has been shown that the extension of this framework to the modulation domain may result in better noise suppression. However, this conclusion has been reached by relying on a minimum statistics approach for the required noise power spectral density (PSD) estimation.Various noise estimation algorithms have been proposed over the years in the speech and audio processing literature. Among these, the widely used minimum statistics approach is known to introduce a time frame lag in the estimated noise spectrum. This can lead to highly inaccurate PSD estimates when the noise behaviour rapidly changes with time, i.e., non-stationary noise. Speech enhancement methods which employ these inaccurate noise PSD estimates tend to perform poorly in the noise suppression task, and in worst cases, may end up deteriorating the noisy speech signal even further. Noise PSD estimation algorithms using a priori information about the noise statistics have been shown to track non-stationary noise better than the conventional algorithms which rely on the minimum statistics approach.In this thesis, we perform noise suppression in the modulation domain with the noise and speech PSD derived from an estimation scheme which employs the a priori information of various speech and noise types. Specifically, codebooks of gain normalized linear prediction coefficients obtained from training on various speech and noise files are used as the a priori information while performing the estimation of the desired PSD. The PSD estimates derived from this codebook approach are used to obtain a minimum mean square error (MMSE) estimate of the clean speech modulation magnitude spectrum, which is then combined with the phase spectrum of the noisy speech to recover the enhanced speech signal. The enhanced speech signal is subjected to various objective experiments for evaluation. Results of these evaluations indicate improvement in noise suppression with the proposed codebook-based modulation domain approach over competing approaches, particularly in cases of nonstationary noise.ii Sommaire Les méthodes conventionnelles de rehaussement de la paroleà canal unique utilisent une structure d'analyse-modification-synthèse (AMS) dans le domaine fréquentiel. Récemment, il aété démontré que l'utilisation de cette structure dans le domaine de la modulation pourrait offrir une meilleure suppression du bruit. Toutefois, cette conclusion aété obtenue en se basant sur une approcheà statistique minimale pour l'estimation de la densité spectrale de puissance (PSD) du bruit ambiant.Plusieurs algorithmes d'estimation de bruit ontété proposés au fil des ans dans la littérature sur le traitement de la parole. D'ordinaire, les méthodes d'estimation de bruit qui se servent d'une approcheà statistique minimale vont créer un décalage temporel dans l'estimation spectrale du bruit. Ce décalage peut engendrer beaucou...

show abstract

Section: Codebook Assisted Speech Enhancementmentioning

confidence: 99%

Section: Codebook Assisted Speech Enhancementmentioning

confidence: 99%

Section: Codebook Assisted Speech Enhancementmentioning

confidence: 99%

Section: Thesis Objective and Contributionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Mani

Champagne

Zhu

2015

2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

show abstract

Speech enhancement using a joint MAP estimation of LP parameters

Wang

Bao

2015

2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

View full text Add to dashboard Cite

Improved CEM for Speech Harmonic Enhancement in Single Channel Noise Suppression

Song

Madhu

2022

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

The periodic nature of voiced speech is often exploited to restore speech harmonics and to increase interharmonic noise suppression. In particular, a recent paper proposed to do this by manipulating the speech harmonic frequencies in the cepstral domain. The manipulations were carried out on the cepstrum of the excitation signal, obtained by the sourcefilter decomposition of speech. This method was termed Cepstral Excitation Manipulation (CEM). In this contribution we further analyse this method, point out its inherent weakness and propose means to overcome it. First of all, it will be shown by both illustrative examples and theoretical analysis that the existing method underestimates the excitation, especially at low signal to noise ratio (SNR) conditions. This inherent weakness leads to speech harmonic weakening and vocoding due to the insufficient noise suppression in the inter-harmonic regions. Then, we propose two modifications to improve the robustness and performance of CEM in low SNR cases. The first modification is to use an instantaneous amplifying factor adapted to the signal, instead of a pre-defined constant, for the excitation cepstrum. The second modification is to smooth the excitation cepstrum to preserve additional fine structure, instead of discarding it. These modifications result in better preservation of speech harmonics, more refined fine structure and higher inter-harmonic noise suppression. Experimental evaluations using a range of standard instrumental metrics conclusively demonstrate that our proposed modifications clearly outperform the existing method, especially in extremely noisy conditions.

show abstract

Modeling the temporal evolution of LPC parameters for codebook-based speech enhancement

Cited by 3 publications

References 5 publications

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Speech enhancement using a joint MAP estimation of LP parameters

Improved CEM for Speech Harmonic Enhancement in Single Channel Noise Suppression

Contact Info

Product

Resources

About