Learning and Plan Refinement in a Knowledge-Based System for Automatic Speech Recognition

Mori, Renato De; Lam, Lily; Gilloux, M.

doi:10.1109/tpami.1987.4767902

Cited by 21 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the speech recognition [8][9][10][11][12][13], there are fifty words has chosen as shown in Table 2. There are 13 personal pronouns, 14 verbs, 5 adjectives, 12 nouns, 3 question words, and 3 yes, no and not for yes/no statements.…”

Section: Words For Speech Recognitionmentioning

confidence: 99%

Sign Language Converter

Arsan¹,

Ulgen²

2015

IJCSES

View full text Add to dashboard Cite

show abstract

Section: Words For Speech Recognitionmentioning

confidence: 99%

Sign Language Converter

Arsan¹,

Ulgen²

2015

IJCSES

View full text Add to dashboard Cite

show abstract

“…Des systèmes basés sur ce principe ont été proposés dans la littérature. Parmi eux, mentionnons : les systèmes « multi-experts » (DeMori, Lam et Gilloux, 1987), les systèmes « sociétés de spécialistes » (Gong, 1988) et le système « multi-opérateurs » (Spalanzani et Selouani 1999 Il faut cependant relever le fait que le phénomène de co-articulation est mal représenté par les unités infra-phonémiques. Pour pallier cet inconvénient, le phone est considéré dans la majorité des cas avec son contexte (gauche et droit) et en incorporant dans la base de connaissances des paramètres différentiels.…”

Section: Constitution De La Base De Connaissancesunclassified

Un système à base de connaissances pour une communication parlée personne-système multilingue

Selouani

2007

rum

View full text Add to dashboard Cite

La tâche de reconnaissance automatique de la parole (RAP), qui est au coeur de la communication parlée Personne-Système, peut être vue comme une gestion de l’information issue de la microstructure acoustique du signal vocal pour la transformer en une information représentée par la macrostructure phonétique implicite. La correspondance avec le moins d’erreurs possible de ces deux structures nécessite une intégration de connaissances a priori sur la macrostructure phonétique dans des systèmes dédiés à la gestion de l’information acoustico-phonétique. Dans cet article, nous abordons des aspects liés tant à la gestion de l’information phonétique véhiculée par le signal vocal qu’à la topologie de systèmes experts capables de conduire des processus de reconnaissance phonémique multilingue. La démarche que nous proposons consiste à enrichir la base de connaissances de ces experts par des indices représentatifs de la majorité des langues humaines afin de rehausser les performances d’identification des macro-classes et des traits phonétiques divers. Les résultats obtenus sur des corpus de logatomes et de phrases en langues française et arabe montrent qu’il est possible d’orienter la conception des systèmes vers une unification du processus de reconnaissance pour l’adapter à une identification phonémique multilingue.Automatic Speech Recognition (ASR) is at the heart of Man-Machine speech communication. It can be seen as a management of the information emanating from the speech acoustical microstructure. This process aims to transform this information in such a way that it can be represented by the phonetic implicit macrostructure. The effective matching between the two structures requires the integration into expert systems, of an a priori knowledge about the phonetic macrostructures. These expert systems are dedicated to the management of acoustic-phonetic information. This paper investigates aspects linked either to the management of phonetic information contained in the speech signal, or to the topology of expert systems that are capable of conducting a multilingual phonemic recognition process. The proposed method consists of feeding the knowledge base of these expert systems with indicative parameters representing the major human languages in order to enhance the identification performance of phonetic macro-classes and features. The results of experiments carried out on corpora composed of both French and Arabic utterances show that it is possible to conceive systems based on the concept of unified recognition processes dedicated to multilingual phonetic identification

show abstract

“…In the speech domain, De Mori [5] has developed the Plan Generation Expert System (PGES) for semi-automatic design of ASR systems. He models the design process as a planning activity.…”

mentioning

confidence: 99%

A Knowledge-Based Design Environment for Speech Recognition Systems

Chitnis

Sarma

1988

IETE Journal of Research

View full text Add to dashboard Cite

The progress in speech technology over the last 30 years has come to a stage, where simple yet practical speech recognition systems could be built. Designing of such systems is an evolutionary process requiring a lot of experimentation. This lengthy and involved process is a major hurdle in developing useful commercial systems like a ,·oice-input telephone dialer. To overcome this problem, we propose the use of a knowledge-based design environment.For analysing a given problem, a framework based on PR and AI concepts is explained using the example of a telephone dialer. Then some representative speech recognition/understanding systems are reviewed to give some idea about the design aspects like the system architecture, PR subtasks involved, AI techniques used etc. Finally the concept of a design environment is explained. The environment is considered as a collection of knowledge-based tools with a global knowledge-base about speech technology.

show abstract

Learning and Plan Refinement in a Knowledge-Based System for Automatic Speech Recognition

Cited by 21 publications

References 10 publications

Sign Language Converter

Sign Language Converter

Un système à base de connaissances pour une communication parlée personne-système multilingue

A Knowledge-Based Design Environment for Speech Recognition Systems

Contact Info

Product

Resources

About