Application of the subspace method to speech recognition

Jalanko, Mahir; Kohonen, Teuvo

doi:10.1109/icassp.1978.1170470

Cited by 6 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fault-mode isolation and mode classification has been done by Artificial Neural Network approach. Artificial Neural Networks has been previously applied in other scientific disciplines such as medicine [Khan 2001], power systems [Adepoju 2007, Haque 2005, business [Mahmood 1995], bioinformatics [Wang 2000[Wang , 2001, image processing [Chalabi 2008, Mahonen 1995, Petersena 2002, civil structures [Efstathiadesa 2007], texture analysis [Kaski 1999], software management [Fong 2007], telecommunication [Kylväjä 2004], and speech recognition [Jalanko 1978]. Development of a prognostic framework based on supervised learning for electronic systems is new.…”

Section: Introductionmentioning

confidence: 99%

Identification of failure modes in portable electronics subjected to mechanical-shock using supervised learning of damage progression

Lall

Gupta

Goebel

2011

2011 IEEE 61st Electronic Components and Technology Conference (ECTC)

View full text Add to dashboard Cite

An anomaly detection and failure mode classification method has been developed for electronic assemblies with multiple failure modes. The presented prognostic health management method targets the pre-failure space of the electronic assembly life to trigger repair or replacement of impending failures. Presently, health monitoring systems focus on reactive diagnostic detection of failure modes. Examples of diagnostic detection include the built in self test and on-board diagnostics. In this paper, damage pre-cursors from timespectral measurements of the electronic assemblies has been measured under applied vibration and shock stimulus. The time-evolution of spectral content of the damage pre-cursors has been studied using joint time frequency analysis in a fullfield manner on the printed circuit assembly. Frequency moments have been used to build a feature vector. Evolution of the feature vector with damage initiation and progression has been studied under shock and vibration. The feature vector from multiple locations in the board assemblies has been mapped into a de-correlated feature space using Sammon's mapping. Several chip-scale packages have been studied, with SAC305 and SAC405 leadfree second-level interconnects. Transient strain has been measured during the drop-event using digital image correlation and high-speed cameras operating at 100,000 fps. Continuity has been monitored simultaneously for failure identification.In addition, explicit finite element models have been developed and various kinds of failure modes have been simulated such as solder ball cracking, trace fracture, package falloff and solder ball failure. The neural net has been trained using simulated data-sets created from error-seeded models with specific failure modes. The neural net has then been used to identify and classify the failure modes in board assemblies experimentally. Supervised learning of multilayer neural net in conjunction with parity has been used to identify the hardseparation boundaries between failure mode clusters in the de-correlated feature space. The assemblies have been crosssectioned to verify the identified failure modes. Crosssections indicate that the experimentally measured failures modes correlate well with the position of the cluster in the decorrelated feature space. IntroductionElectronics in avionics, military, defense, automobile, implantable medical applications experience harsh environments of mechanical shock and vibration for extended

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of failure modes in portable electronics subjected to mechanical-shock using supervised learning of damage progression

Lall

Gupta

Goebel

2011

2011 IEEE 61st Electronic Components and Technology Conference (ECTC)

View full text Add to dashboard Cite

show abstract

“…The pattern vectors were formed by concatenation of two 15-element spectra taken at a temporal interval of 30 ms. Such a concatenation was needed in an integrated system described elsewhere (2)(3)(4) Separate sdbspaces were defined for each of the nasals In n p/ but due to their poor mutual discrimination their recognition accuracies will be reported here as one group. The result, however, is better than if they were included in the same subspace.…”

Section: Tee Practical Applicationmentioning

confidence: 99%

“…Its applicability to the recognition of phonemes from continuous speech has been demonstrated in a few previous works (2)(3)(4). In this paper, the subspace method is developed further to yield results of practical value.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Spectral classification of phonemes by learning subspaces

Kohonen¹,

Németh²,

Bry³

et al.

ICASSP '79. IEEE International Conference on Acoustics, Speech, and Signal Processing

Self Cite

View full text Add to dashboard Cite

A new pattern recognition scheme with learning ability is introduced, and its application to the labeling of phonemes is reported. The basic classification algorithm is known as the subspace method in which classes of patterns are defined as linear vector subspaces spanned by the prototypes, and the class affiliation of an unknown pattern vector is decided by comparison of its orthogonal projections on the various subspaces. This method is here modified in two ways. In one of them, the prototype patterns are selected conditionally according to classification results obtained during training. In the second modification the subspaces are rotated in proper directions in the training procedure, depending on the classification results. By means of these methods, for the average accuracy of classification with 15 phonemic classes from continuous Finnish speech, a value of about 80 per cent was obtained.

show abstract

Self-organized mapping of failure modes in portable electronics subjected to drop and shock

Lall

Gupta

Panchagade

2010

2010 Proceedings 60th Electronic Components and Technology Conference (ECTC)

View full text Add to dashboard Cite

Portable electronic products subjected to transient shock may exhibit multiple failure modes in vicinity of the interconnects. Failure is often diagnosed by loss of functionality using techniques including the built-in self test, which provides limited insight into reliability and remaining useful life. In this paper prognostic framework for electronic systems has been developed with neural network based self organizing maps. The presented approach resides in the pre-failure space with a focus on electronic systems with multiple failure modes. Unsupervised learning of the neural net has been used to train the neural net for identification of individual failure modes. Feature vectors have been developed based on damage pre-cursors from time-spectral measurements. The clustered damage pre-cursors have been correlated with failure modes of the underlying damage. Several chip-scale packages have been studied, with leadfree second-level interconnects including SAC305, SAC405 alloys.

show abstract

Application of the subspace method to speech recognition

Cited by 6 publications

References 4 publications

Identification of failure modes in portable electronics subjected to mechanical-shock using supervised learning of damage progression

Identification of failure modes in portable electronics subjected to mechanical-shock using supervised learning of damage progression

Spectral classification of phonemes by learning subspaces

Self-organized mapping of failure modes in portable electronics subjected to drop and shock

Contact Info

Product

Resources

About