Compressive sensing framework for speech signal synthesis using a hybrid dictionary

Wang, Yue; Xu, Zhixing; Li, Gang; Chang, Liping; Hong, Chuanrong

doi:10.1109/cisp.2011.6100691

Cited by 14 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DCT is also used as a sparsifying basis for many applications (Kassim et al 2012;Gunawan et al 2011). Sometimes appropriate sparsifying basis is designed (dictionary design) based on the characteristics of the signal to be acquired by combining various transforms (Wang et al 2011). In yet another method, the dictionary/sparifying frame is learned by a dictionary learning for efficient sparse representation of real world signals which are compressible (Jafari and Plumbey 2008;Aharon et al 2006).…”

Section: Cs Mathematical Frameworkmentioning

confidence: 99%

“…It is less complex than a learned signal adaptive dictionary, but at the same time extracts signal parameters to model the system more accurately. As a linear combination of the atoms from the hybrid dictionary is used to model each speech segment, even the transitions are efficiently represented by this dictionary (Wang et al 2011). …”

Section: Quantizing Compressive Sensing Measurementsmentioning

confidence: 99%

“…3 was used for simulations except for the fact that instead of DCT, a hybrid dictionary formed by the approach mentioned in Wang et al (2011) sparsified the speech signals. Similarly at the decoder, the inverse sparsifying matrix corresponding to the hybrid dictionary, used at the encoder, was used.…”

Section: Cs Coding Using Hybrid Dictionary As Sparsifying Transform (mentioning

confidence: 99%

“…Using Hybrid Dictionary as Sparsifying Matrix further improving the decoded speech quality and in-order to assess the effect of the sparsifying transform on the performance of the system, as mentioned in Sect. 1, a hybrid dictionary formed from DFT and LPC basis (Wang et al 2011) was used as sparsifying transform instead of DCT. A dictionary learned from the speech signal itself like K-SVD Aharon et al (2006), greedy adaptive dictionary (GAD) (Jafari and Plumbey 2008;Jafari 2011, 2009) etc were not preferred as the whole dictionary needs to be transmitted across the channel for each speech signal under consideration.…”

Section: Quantizing Compressive Sensing Measurementsmentioning

confidence: 99%

“…A hybrid dictionary designed from discrete fourier transform basis (DFT) and linear prediction coefficients (LPC) estimated from the speech signal was used to have more accurate sparse representation of the underlying speech segment (Wang et al 2011). In general, an appropriate dictionary is chosen based on a mathematical model of the data-dictionary design, or by learning a dictionary from a set of realizations of the data to perform best on a training set-dictionary learning (Rubinstein et al 2010).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Simultaneous speech coding and de-noising in a dictionary based quantized CS framework

Ramdas

Gorthi

Mishra

2016

Int J Speech Technol

View full text Add to dashboard Cite

Speech compression or speech coding is inevitable for effective communication of speech signals in resource limited scenarios and researcher's have been working on achieving lower and lower transmission bit rates (BR) without much compromise on the quality of speech. Medium BR hybrid speech coding schemes have gained much interest in the recent years with most of them based on CELP, the basic medium bit-rate coding scheme. In this work, we provide an insight to the capabilities of compressive sensing (CS) in speech processing and propose a novel idea in the quantized framework. Three major aspects demonstrated in this paper are (1) Inherent denoising of noisy speech by the CS based coder along with compression (2) Quantization of CS measurements to achieve medium transmission bit-rates and (3) Enhancement of quality and compression performance of the coder with better sparse representations of speech using dictionaries. The results indicate that the proposed scheme offers better compression in comparison with basic Gaussian codebook CELP. The CS scheme has the added advantage of inherent noise suppression and provides more robustness to background noise in comparison with parameter extraction based medium bit-rate speech coding systems.

show abstract

Section: Cs Mathematical Frameworkmentioning

confidence: 99%

Section: Quantizing Compressive Sensing Measurementsmentioning

confidence: 99%

Section: Cs Coding Using Hybrid Dictionary As Sparsifying Transform (mentioning

confidence: 99%

Section: Quantizing Compressive Sensing Measurementsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Simultaneous speech coding and de-noising in a dictionary based quantized CS framework

Ramdas

Gorthi

Mishra

2016

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

Variation Measurement of SNR and MSE for Musical Instruments Signal Compressed Using Compressive Sensing

Kumari

Sujediya

Upadhyaya³

2020

Algorithms for Intelligent Systems

View full text Add to dashboard Cite

A scalable speech coding scheme using compressive sensing and orthogonal mapping based vector quantization

Sankar

Sathidevi

2019

Heliyon

View full text Add to dashboard Cite

A novel scalable speech coding scheme based on Compressive Sensing (CS), which can operate at bit rates from 3.275 to 7.275 kbps is designed and implemented in this paper. The CS based speech coding offers the benefit of combined compression and encryption with inherent de-noising and bit rate scalability. The non-stationary nature of speech signal causes the recovery process from CS measurements very complex due to the variation in sparsifying bases. In this work, the complexity of the recovery process is reduced by assigning a suitable basis to each frame of the speech signal based on its statistical properties. As the quality of the reconstructed speech depends on the sensing matrix used at the transmitter, a variant of Binary Permuted Block Diagonal (BPBD) matrix is also proposed here which offers a better performance than that of the commonly used Gaussian random matrix. To improve the coding efficiency, formant filter coefficients are quantized using the conventional Vector Quantization (VQ) and an orthogonal mapping based VQ is developed for the quantization of CS measurements. The proposed coding scheme offers the listening quality for reconstructed speech similar to that of Adaptive Multi rate-Narrowband (AMR-NB) codec at 6.7 kbps and Enhanced Voice Services (EVS) at 7.2 kbps. A separate de-noising block is not required in the proposed coding scheme due to the inherent de-noising property of CS. Scalability in bit rate is achieved in the proposed method by varying the number of random measurements and the number of levels for orthogonal mapping in the VQ stage of measurements.

show abstract

Compressive sensing framework for speech signal synthesis using a hybrid dictionary

Cited by 14 publications

References 10 publications

Simultaneous speech coding and de-noising in a dictionary based quantized CS framework

Simultaneous speech coding and de-noising in a dictionary based quantized CS framework

Variation Measurement of SNR and MSE for Musical Instruments Signal Compressed Using Compressive Sensing

A scalable speech coding scheme using compressive sensing and orthogonal mapping based vector quantization

Contact Info

Product

Resources

About