Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

2 Archives of Acoustics

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

An Acoustic Study of the Emphatic Occlusive [t] in School-Going Children with Cleft Palate or Cleft Lip

100%

Baazi K. , Guerti M.

Archives of Acoustics

2022

tom Vol. 47, No. 2

141--149

The aim of this acoustic study is to analyse the phoneme [t] produced by school children surgically operated on for the cleft palate or cleft lip, in order to examine their vocal characteristics, to provide speech therapists with numerous concrete analyses of voice and speech, to effectively support them and to prevent some serious outcomes on their psychological and academic development. The motivation for this study was mainly stemming from the difficulties that Algerian schoolchildren with clefts encounter in the pronunciation of this phoneme. To carry out the study, several acoustic parameters were investigated in terms of the fundamental frequency F0, the first three formants F1, F2, and F3, the energy E0, the Voice Onset Time (VOT), the durations [CV] and [V] of the subsequent vowel [a]. For the analysis, further important parameters in the field of pathological speech were deployed, namely the degree of disturbance of F0 (jitter), the degree of disturbance of intensity (shimmer) and the HNR (Harmonics to Noise Ratio). Results revealed disturbance in the values of F1, F2, and F3 and stability in the values of F0. Another important reported aspect is the increase in the value of the VOT due to the difficulties in controlling the plosives’ successive closure and release.

Conditional Random Fields Applied to Arabic Orthographic-Phonetic Transcription

100%

Cherifi E.-H. , Guerti M.

Archives of Acoustics

2021

tom Vol. 46, No. 2

237--247

Orthographic-To-Phonetic (O2P) Transcription is the process of learning the relationship between the written word and its phonetic transcription. It is a necessary part of Text-To-Speech (TTS) systems and it plays an important role in handling Out-Of-Vocabulary (OOV) words in Automatic Speech Recognition systems. The O2P is a complex task, because for many languages, the correspondence between the orthography and its phonetic transcription is not completely consistent. Over time, the techniques used to tackle this problem have evolved, from earlier rules based systems to the current more sophisticated machine learning approaches. In this paper, we propose an approach for Arabic O2P Conversion based on a probabilistic method: Conditional Random Fields (CRF). We discuss the results and experiments of this method apply on a pronunciation dictionary of the Most Commonly used Arabic Words, a database that we called (MCAW-Dic). MCAW-Dic contains over 35 000 words in Modern Standard Arabic (MSA) and their pronunciation, a database that we have developed by ourselves assisted by phoneticians and linguists from the University of Tlemcen. The results achieved are very satisfactory and point the way towards future innovations. Indeed, in all our tests, the score was between 11 and 15% error rate on the transcription of phonemes (Phoneme Error Rate). We could improve this result by including a large context, but in this case, we encountered memory limitations and calculation difficulties.