Direct estimation of the vocal tract shape by inverse filtering of acoustic speech waveforms

Wakita, Hisashi

doi:10.1109/tau.1973.1162506

Cited by 215 publications

(95 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…and indirect techniques where speech signal is used for vocal tract shape estimation. The indirect techniques include use of formants [15]- [17], lip impedance measurement [18] and LPC analysis of speech [19] [20]. With a distinct advantage of LPC analysis, that the real time VTS can be obtained, this method has been popularly used for adult speakers.…”

Section: Introductionmentioning

confidence: 99%

“…With a distinct advantage of LPC analysis, that the real time VTS can be obtained, this method has been popularly used for adult speakers. Investigation has been done towards obtaining optimum algorithm parameters for LPC analysis using Wakita's method [19]. The obtained parameters found are vocal tract length, LPC prediction order and sampling frequency of speech signal acquired from children in various age groups [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Validation of Optimum Algorithm Parameters Required to Estimate Vocal Tract Shape for Children Using LPC Analysis

Wankhede¹,

Shah²

2014

OALib

View full text Add to dashboard Cite

Severe or profound deafness in hearing impaired children, can curb their ability to speak due to the lack of auditory feedback. There has been a considerable attempt in developing commercial speech training aids for such children which give feedback of acoustic and articulatory parameters. Speech training aids based on visual feedback of vocal tract shape (VTS) are reported to be useful for the improvement in speech production. Since realistic VTS estimation for adult speakers and their validation has already been done successfully, VTS estimation is now necessarily required in case of children too, so that they get trained in speech at an early age. The investigation on vocal tract shape estimation based on LPC analysis of speech by appropriately selecting some of the algorithm parameters such as vocal tract length, LPC order, and speech sampling rate has been done in our previous work. This paper attempts to validate the obtained results for vocal tract shapes corresponding to certain recorded vowels from children belonging to specific age groups. Since MRI images of VTS are unavailable for articulating children, validation of our results is based on the results from researchers who have used other indirect techniques to obtain VTS.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Validation of Optimum Algorithm Parameters Required to Estimate Vocal Tract Shape for Children Using LPC Analysis

Wankhede¹,

Shah²

2014

OALib

View full text Add to dashboard Cite

show abstract

“…VTS vectors corresponding to the segments were computed using inverse filtering [11]. The VTS-SS(spectral shape) pairs were generated by a program implemented in 'Matlab' and a set of dat data files were created for quantal vowels .…”

Section: Resultsmentioning

confidence: 99%

A comparison of modified k-means (MKM) and NN based real time adaptive clustering algorithms for articulatory space codebook formation

Ananthakrishnan

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

View full text Add to dashboard Cite

This paper proposes the use of a neural network based real time adaptive clustering* algorithm for the formation of a codebook of limited set of acoustical representation of finite set of vocal tract shapes from an articulatory space. Modified k-means algorithm (MKM) used for clustering nearly 10000 vocal tract shapes into 1000 cluster centers to form a codebook of articulatory shapes is computationally intensive for our application . An investigative study on the use of NN based algorithm over MKM algorithm at the peripheral level , for our application on Computer Aided Pronunciation-education, suggests the former for less intensive computation, with the possibility of improving the performance of the system by implementing the algorithm using a dedicated neural computer. In this paper, preliminary results of this study are reported.

show abstract

“…Hence, indexing of the non-uniform configurations would use a lower number of bits. Adequation with articulatory modeling -As pointed out in the introduction, the NUT lattice idea originally arose from the study of the analogy between lattice filtering and acoustic filtering in lossless tubes [2,4]. While the purpose of the present article was to describe and explore NUT lattices from a pure signal processing point of view, further experiments are needed to determine whether the second optimization layer is able to capture actual acoustic phenomena (e.g., nodes of stationary sound waves, or speakerspecific relative formant positions).…”

Section: Potential Applicationsmentioning

confidence: 99%

“…Their parameters, the reflection coefficients, have a good robustness to noise and quantization effects [1]. These filters also present a formal analogy with the process of wave propagation into lossless discrete acoustic tube models (possibly used as vocal tract models) [2]. But they don't incorporate any other a priori knowledge about the process they represent.…”

Section: Introductionmentioning

confidence: 99%

Signal modeling with non-uniform topology lattice filters

Krstulović

Bimbot

2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)

View full text Add to dashboard Cite

This article presents a new class of constrained and specialized Auto-Regressive (AR) processes. They are derived from lattice filters where some reflection coefficients are forced to zero at a priori locations. Optimizing the filter topology allows to build parametric spectral models that have a greater number of poles than the number of parameters needed to describe their location. These NUT (Non-Uniform Topology) models are assessed by evaluating the reduction of modeling error with respect to conventional AR models.

show abstract

Direct estimation of the vocal tract shape by inverse filtering of acoustic speech waveforms

Cited by 215 publications

References 8 publications

Validation of Optimum Algorithm Parameters Required to Estimate Vocal Tract Shape for Children Using LPC Analysis

Validation of Optimum Algorithm Parameters Required to Estimate Vocal Tract Shape for Children Using LPC Analysis

A comparison of modified k-means (MKM) and NN based real time adaptive clustering algorithms for articulatory space codebook formation

Signal modeling with non-uniform topology lattice filters

Contact Info

Product

Resources

About