Robust Detection of Phone Boundaries Using Model Selection Criteria With Few Observations

Almpanidis, George; Kotti, Margarita; Kotropoulos, Constantine

doi:10.1109/tasl.2008.2009162

Cited by 20 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The most common approach is based on the segmentation on the basis of changing of spectral variation function [2,31,32]. In the most available descriptions of the speech segmentation algorithms only own modality of the speech signal is used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic speech segmentation using throat-acoustic correlation coefficients

et al. 2016

View full text Add to dashboard Cite

This work considers one of the approaches to the solution of the task of discrete speech signal automatic segmentation. The aim of this work is to construct such an algorithm which should meet the following requirements: segmentation of a signal into acoustically homogeneous segments, high accuracy and segmentation speed, unambiguity and reproducibility of segmentation results, lack of necessity of preliminary training with the use of a special set consisting of manually segmented signals. Development of the algorithm which corresponds to the given requirements was conditioned by the necessity of formation of automatically segmented speech databases that have a large volume. One of the new approaches to the solution of this task is viewed in this article. For this purpose we use the new type of informative features named TAC-coe cients (Throat-Acoustic Correlation coe cients) which provide su cient segmentation accuracy and eciency.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The quality of the speech synthesis and recognition results depends considerably on its qualitative solution. Di erent algorithms for speech signal automatic segmentation are already available now [1][2][3][31][32][33][34]. Many available algorithms have their certain advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

Automatic speech segmentation using throat-acoustic correlation coefficients

et al. 2016

View full text Add to dashboard Cite

show abstract

“…These variances are a basis for formulating a Generalized Likelihood Ratio Test (GLRT) related to a change in the signal power spectrum density over the analysed period of time. Almanidis et al (2008;2009) presented a hybrid algorithm known as the Model Selection Criterion (MSC), using a Bayesian Information Criterion (BIC) and Kullback-Leibler information. This method requires MFCC parameterisation of the speech signal, constructing a model of speech signal segments and performing boundary detection.…”

Section: Introductionmentioning

confidence: 99%

“…The efficiency of defining interphonemic transitions by means of supervised algorithms, with the assumed tolerance of up to 20 ms, reaches 93%, while for unsupervised algorithms it is up to 75%, with the false acceptance error of 2% (Almanidis et al, 2008;2009). This advantage of supervised algorithms is a consequence of using information about the phonetic content.…”

Section: Introductionmentioning

confidence: 99%

Automatic speech signal segmentation based on the innovation adaptive filter

Makowski

Hossa

2014

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Speech segmentation is an essential stage in designing automatic speech recognition systems and one can find several algorithms proposed in the literature. It is a difficult problem, as speech is immensely variable. The aim of the authors' studies was to design an algorithm that could be employed at the stage of automatic speech recognition. This would make it possible to avoid some problems related to speech signal parametrization. Posing the problem in such a way requires the algorithm to be capable of working in real time. The only such algorithm was proposed by Tyagi et al., (2006), and it is a modified version of Brandt's algorithm. The article presents a new algorithm for unsupervised automatic speech signal segmentation. It performs segmentation without access to information about the phonetic content of the utterances, relying exclusively on second-order statistics of a speech signal. The starting point for the proposed method is time-varying Schur coefficients of an innovation adaptive filter. The Schur algorithm is known to be fast, precise, stable and capable of rapidly tracking changes in second order signal statistics. A transfer from one phoneme to another in the speech signal always indicates a change in signal statistics caused by vocal track changes. In order to allow for the properties of human hearing, detection of inter-phoneme boundaries is performed based on statistics defined on the mel spectrum determined from the reflection coefficients. The paper presents the structure of the algorithm, defines its properties, lists parameter values, describes detection efficiency results, and compares them with those for another algorithm. The obtained segmentation results, are satisfactory.

show abstract

“…Some papers also propose the text-independent phonetic segmentation as in [8,9], which detect phone boundaries only using acoustic features. However, our main target applications are those in which linguistic information is available, such as TTS or accent conversion.…”

Section: Introductionmentioning

confidence: 99%

Phonetic segmentation using statistical correction and multi-resolution fusion

Zhao

Soon

Koh

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper focuses on the generation of accurate phonetic segmentations. Statistical methods based on absolute and relative correction are discussed and experimented on both monophone and biphone models to improve the segmentation results. The influence of search range on the statistical correction process is studied and a state selection technique is used to enhance the correction results. This paper also explores the influence of resolution (stepsize) of HMMs and proposes a multi-resolution fusion process to further refine the statistically corrected results. Improvements of segmentation results in terms of segmentation accuracy, mean absolute error (MAE), and root mean square error (RMSE) can be observed by applying the proposed refinement methods.

show abstract

Robust Detection of Phone Boundaries Using Model Selection Criteria With Few Observations

Cited by 20 publications

References 34 publications

Automatic speech segmentation using throat-acoustic correlation coefficients

Automatic speech segmentation using throat-acoustic correlation coefficients

Automatic speech signal segmentation based on the innovation adaptive filter

Phonetic segmentation using statistical correction and multi-resolution fusion

Contact Info

Product

Resources

About