Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 9

first rewind previous Page / 1 next fast forward last

Search results

help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

A Multi-Layer Transcription Model – concept outline

100%
Śledziński D.
Lingua Posnaniensis
|
2022
|
vol. 64
|
issue 1
49-71
EN
This paper discusses the assumptions of a Multi-Layer Transcription Model (hereinafter: MLTM). The solution presented is an advanced grapheme-to-phoneme (G2P) conversion method that can be implemented in technical applications, such as automatic speech recognition and synthesis systems. The features of MLTM also facilitate the application of text-to-transcription conversion in linguistic research. The model presented here is the basis for multi-step processing of the orthographic representation of words with those being transcribed gradually. The consecutive stages of the procedure include, among other things, identification of multi-character phonemes, voicing status change, and consonant clusters simplification. The multi-layer model described in this paper makes it possible to assign individual phonetic processes (for example assimilation), as well as other types of transformation, to particular layers. As a result, the set of rules becomes more transparent. Moreover, the rules related to any process can be modified independently of the rules connected with other forms of transformation, provided that the latter have been assigned to a different layer. These properties of the multi-layer transcription model in question provide crucial advantages for the solutions based on it, such as their flexibility and transparency. There are no assumptions in the model about the applicable number of layers, their functions, or the number of rules defined in each layer. A special mechanism used for the implementation of the MLTM concept enables projection of individual characters onto either a phonemic or a phonetic transcript (obtained after processing in the final layer of the MLTM-based system has been completed). The solution presented in this text has been implemented for the Polish language, however, it is not impossible to use the same model for other languages.
2
Publication available in full text mode
Content available

Wielowarstwowy model podziału wyrazów ortograficznych języka polskiego na sylaby

100%
Śledziński D.
Polonica
|
2018
|
vol. 38
175-198
EN
This paper presents a model for the syllabification of Polish words written in orthographic form. It raises some significant issues related to syllabification, including the linguistic definition of a syllable and certain phonological principles: the Sonority Sequencing Principle and the Maximal Onset Principle. The article describes the steps of a designed syllabification procedure. This procedure provides four layers of syllable boundary placement. The first layer is related to the morphological structure of the word (it concerns mainly boundaries between a prefix and a stem). The structure of the rules in the first layer is based on the initial and final strings in words. The goal of the second layer is to put boundaries between syllable nuclei. The next layer modifies the boundaries that result from the phonological principles. The last layer places boundaries resulting from the phonological principles. Rules applied earlier mask rules on the succeeding layers. The article also presents a structure of rules based on probability. A description of static syllabification systems is also given - these work much faster, but it is not possible to modify the rules associated with them. The last described feature of the presented solution is the ability to create generative systems.
3
Publication available in full text mode
Content available

Percepcja audytywna, właściwości akustyczne oraz cechy dystrybucyjne sylab w języku polskim

100%
Śledziński D.
Investigationes Linguisticae
|
2015
|
issue 32
106-123
EN
This paper presents experiments concerning properties of selected CV syllables. Acoustic speech signal related to particular syllables was analyzed using artificial neural networks. The goal of the analyses was to investigate whether realizations of particular syllables retain acoustic features distinctive of these syllables. Aditionally, a perception test aiming at identification of the same syllable set was carried out. In the test we analyzed to which degree it is possible to identify syllables isolated from the linguistic context. The paper discusses also results on distributional properties of syllables which indicate that such properties may play a significant role in speech perception.
PL
This paper presents experiments concerning properties of selected CV syllables. Acoustic speech signal related to particular syllables was analyzed using artificial neural networks. The goal of the analyses was to investigate whether realizations of particular syllables retain acoustic features distinctive of these syllables. Aditionally, a perception test aiming at identification of the same syllable set was carried out. In the test we analyzed to which degree it is possible to identify syllables isolated from the linguistic context. The paper discusses also results on distributional properties of syllables which indicate that such properties may play a significant role in speech perception.Percepcja audytywna, właściwości akustyczne oraz cechy dystrybucyjne sylab w języku polskim
4
Publication available in full text mode
Content available

Fonetyczno-akustyczna analiza struktury sylaby w języku polskim na potrzeby technologii mowy

100%
Śledziński D.
Investigationes Linguisticae
|
2008
|
vol. 16
219-240
EN
This paper presents results of investigations concerning the role of syllable as the main unit for automatic speech recognition and speech synthesis for Polish. Research reveals that the acoustic properties of the particular syllable make it easy detectable in the speech signal. The artificial neural networks were used for classification tasks. Also auditory test showed that use of syllables is good solution for speech synthesis. The article presents parts of author`s doctor thesis: ‘Acoustic-phonetic analysis of syllable in Polish for use in speech technology’. 
5
Publication available in full text mode
Content available

Badanie odczucia subiektywnego związanego z dzieleniem na sylaby wyrazów języka polskiego - podział grup złożonych ze spółgłosek właściwych

100%
Śledziński D.
Acta Universitatis Lodziensis. Folia Linguistica
|
2017
|
vol. 51
|
issue 1
93-107
EN
This paper presents the results of an investigation of subjective feelings related to the syllabification of Polish words written in orthographic form. The results presented are limited to consonant clusters composed only of obstruents, located within words. In previous articles the author has shown that, despite the presence of numerous long consonant clustersin Polish, the process of syllabification may be based on phonological principles: the sonority principle and the principle of maximal onset. It was also shown that the phonological rules sometimes suggest different solutions than the morphological structure, particularly at boundaries between a prefix and a stem. The main goal of the present investigations was to verify whether the syllabification based on phonology differs from that based on subjective feelings. The article also refers to some statistical properties of consonant clusters, with the aim of verifying whether the main results presented here are related to those properties.
PL
-
6
Publication available in full text mode
Content available

Badanie odczucia subiektywnego związanego z dzieleniem na sylaby wyrazów języka polskiego ― podział grup złożonych ze spółgłosek sonornych

100%
Śledziński D.
Acta Universitatis Lodziensis. Folia Linguistica
|
2017
|
vol. 51
|
issue 1
109-127
EN
This paper presents the results of an investigation of subjective feelings related to the syllabification of Polish words written in orthographic form. The results presented are limited to consonant clusters that contain at least one sonorant. This is a continuation of the author’s previous paper: An investigation of subjective feelings related to syllabification in Polish - the division of consonant clusters composed of obstruents. In previous articles the author has shown that, despite the presence of numerous long consonant clusters in Polish, the process of syllabification may be based on phonological principles: the sonority principle and the principle of maximal onset. The main goal of the present investigations was to verify whether the syllabification based on phonology differs from that based on subjective feelings. The article also refers to some statistical properties of consonant clusters, with the aim of verifying whether the results presented here are related to those properties.
PL
-
7
Publication available in full text mode
Content available

Badanie poczucia subiektywnego związanego z dzieleniem na sylaby wyrazów języka polskiego – podział wieloelementowych grup spółgłoskowych

100%
Śledziński D.
Poznańskie Studia Polonistyczne. Seria Językoznawcza
|
2017
|
vol. 24
|
issue 2
195-214
PL
This paper presents the results of a preliminary investigation of subjective feelings related to the syllabification of Polish words written in orthographic form. The results are part of a wider study, and the data presented here are limited to polysegmental word-internal consonant clusters. In the author’s previous articles it was noted that some morphological boundaries are perceived as syllable boundaries – particularly boundaries between a prefix and a stem. The words that contain such boundaries were excluded from the investigation. The main goal was to verify whether the phonostatistical properties of consonant clusters influence subjective feelings related to syllabification. The investigated statistical proprieties concern the frequency of occurrence of consonant clusters, and of parts of them at the beginning of words, in the text corpus. Another goal was to verify whether the syllabification based on phonology differs from that based on subjective feelings.
8
Publication available in full text mode
Content available

Odwołanie do fonologii w procesie dzielenia na sylaby wyrazów ortograficznych języka polskiego

100%
Śledziński D.
Investigationes Linguisticae
|
2017
|
vol. 37
59-72
EN
This paper presents selected topics related to automatic syllabification in Polish. Several factors have been taken into consideration in designing a syllabification system for Polish – phonological principles, subjective feelings, and the morphological structure of words. The phonological principles, primarily the sonority principle, refer to the phonetic definition of a syllable, but subjective feelings sometimes suggest another division. The main goal of this article is to describe aspects of the syllabification system that refer to phonological principles. These principles refer to consonant clusters located within words, hence a method of extracting such clusters is given. This method is based on marking letters in the orthographic form of words that represent syllable nuclei. This task is somewhat complicated by the fact that some Polish letters that usually stand for vowels also represent consonants in particular neighborhoods. A method of masking the division based on phonology is also given. It is possible to apply rules that reflect subjective feelings, and the resulting division may differ from the division based on phonology.
PL
W artykule omówiono wybrane zagadnienia związane z procesem automatycznego dzielenia na sylaby tekstów ortograficznych w języku polskim. Przy projektowaniu systemu sylabifikującego uwzględniono kilka istotnych czynników: zasady fonologiczne,odczucia subiektywne, strukturęmorfologiczna wyrazów. Zasady fonologiczne – przede wszystkim zasada sonorności – odnosi się do fonetycznej definicji sylaby. W niniejszej publikacji skoncentrowano się na aspektach działania systemu związanych z odwoływaniem się do zasad fonologicznych. Te zasady odnoszą się do wewnątrzwyrazowych grup spółgłoskowych, które są wyznaczane na podstawie informacji o lokalizacji liter odpowiadających ośrodkom sylab. To zadanie jest nieco utrudnione faktem, że w języku polskim niektóre litery, które zazwyczaj oznaczają samogłoski, w określonym kontekście oznaczają spółgłoski. W artykule omówiono również metodę przesłaniania podziału wynikającego z fonologii. Można stosować reguły które odnoszą się do odczucia subiektywnego i podział z niego wynikający różni się od podziału wynikającego z fonologii.
9
Publication available in full text mode
Content available

Projekcja ortograficznych form wewnątrzwyrazowych grup spółgłoskowych na transkrypcję fonologiczną na potrzeby systemu dzielenia na sylaby wyrazów języka polskiego

100%
Śledziński D.
Investigationes Linguisticae
|
2016
|
issue 34
51-72
EN
This paper presents a module forming part of a currently developed syllabification system for Polish. The main purpose of this module is to map the orthographic form of consonant clusters located within words to their phonological transcription. The mapping is very precise – each letter in the orthographic form is assigned to a particular phoneme or group of phonemes. The main goal is to allow phonological principles – the sonority principle and the principle of maximal onset – to be applied directly to words written in orthographic form. These principles are based on a phonological sonority scale that assigns abstract numbers to speech sounds. These numbers reflect certain phonetic features associated with the sounds, chiefly the degree of opening of the vocal tract. Thecomplex relationships between the orthographic and phonological forms of Polish words mean that the assignment of values of the sonority scale directly to letters is not possible.
PL
W niniejszym artykule omówiono moduł, który jest częścią rozwijanego systemu dzielenia na sylaby dla języka polskiego. Zadanie tego modułu polega na odwzorowaniu wewnątrzwyrazowych grup spółgłoskowych zapisanych w formie ortograficznej na zapis w transkrypcji fonologicznej. Odwzorowanie jest bardzo precyzyjne – poszczególne litery zapisu ortograficznego wewnątrzwyrazowych grup spółgłoskowych są przypisane do poszczególnych fonemów. Podstawowy cel omawianego modułu związany jest z potrzebą stosowania zasad fonologicznych (zasady sonorności oraz zasady maksymalnego nagłosu) w odniesieniu do wyrazów ortograficznych. Te zasady bazują na fonologicznej skali sonorności, która przypisuje do dźwięków mowy abstrakcyjne wartości liczbowe. Te wartości odzwierciedlają cechy fonetyczne właściwe dla poszczególnych dźwięków mowy – przede wszystkim stopień rozwarcia narządów artykulacyjnych. W języku polskim występują złożone relacje między płaszczyzną ortograficzną i płaszczyzną fonologiczną. Dlatego przypisywanie wartości sonorności bezpośrednio do liter ortograficznych nie jest możliwe.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.