Claim Missing Document
Check
Articles

The Performance of OpenL as an AI Recognition of Interdental Fricatives [θ] and [ð] in Indonesian-Accented English Sufi, M. Iqbal Farabi; Tengku Syarfina
Journal of Applied Linguistics Vol. 5 No. 2 (2026): January 2026
Publisher : English Lecturers and Teachers Association (ELTA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52622/joal.v5i2.608

Abstract

This study investigates how Artificial Intelligence (AI) systems recognize the English interdental fricatives /θ/ and /ð/ in Indonesian-accented speech. Because these sounds are absent from the Indonesian phonological inventory, Indonesian learners often experience difficulty producing them, which may affect intelligibility and AI recognition. Using a qualitative phonetic analysis with AI-based comparison, speech data from six Indonesian learners of English and one native speaker were collected. The recordings were analyzed using Praat to examine acoustic characteristics and OpenL to generate speech-to-IPA transcriptions. The results show that many learner productions lacked sustained fricative turbulence, indicating non-target realizations of interdental fricatives. OpenL generally reflected these acoustic deviations rather than producing canonical forms, suggesting limited sensitivity to subtle fricative cues. Overall, the findings reveal an intersection between human phonetic challenges and technological limitations in current ASR systems, highlighting the need for accent-inclusive training data and focused pronunciation instruction to improve both intelligibility and AI speech recognition performance. Keywords : Interdental fricatives; Indonesian-accented English; OpenL
AN EXPLORATORY ACOUSTIC ANALYSIS OF ENGLISH INTERROGATIVES BY NATIVE DANISH AND INDONESIAN CHINESE MALE SPEAKERS Utami, Tri; Syarfina, Tengku
Jurnal Suluh Pendidikan Vol 14 No 1 (2026): Maret 2026
Publisher : Fakultas Keguruan dan Ilmu Pendidikan, Universitas HKBP Nommensen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36655/jsp.v14i1.2076

Abstract

This exploratory study investigates the acoustic realization of English interrogative sentences produced by native Danish and Indonesian Chinese male speakers. The study aims to identify cross-linguistic tendencies in second language (L2) prosody through the analysis of three acoustic parameters: duration, intensity, and pitch. The target sentence “Do you like coffee?” was recorded under controlled conditions and analyzed using Praat software. Although based on a very small sample (two speakers per group), the analysis revealed distinct prosodic tendencies between the two groups. The Danish speakers generally produced shorter utterances with greater pitch and intensity variation, while the Indonesian Chinese speakers tended to produce longer and more uniform duration patterns with narrower pitch ranges. These patterns may reflect influences from each group’s first language rhythmic and tonal systems, though the results remain exploratory and non-generalizable due to the limited data. The findings provide preliminary insights into cross-linguistic tendencies in L2 English interrogative prosody and highlight the need for replication with larger participant groups. Pedagogically, the study underscores the potential relevance of prosody-focused pronunciation instruction for learners from syllable-timed and tonal language backgrounds.
COMPARATIVE ACOUSTIC ANALYSIS OF ENGLISH YES/NO QUESTION INTONATION, DURATION, AND INTENSITY FOR A NATIVE BRITISH ENGLISH SPEAKER AND A JAVANESE SPEAKER USING PRAAT Fanisa, Naza; Syarfina, Tengku
Jurnal Suluh Pendidikan Vol 14 No 1 (2026): Maret 2026
Publisher : Fakultas Keguruan dan Ilmu Pendidikan, Universitas HKBP Nommensen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36655/jsp.v14i1.2095

Abstract

Prosodic features such as intonation, duration, and intensity play a crucial role in spoken communication and are often influenced by a speaker’s first language when using a second language. This study aims to acoustically compare the production of an English yes/no question by a native British English speaker and a Javanese speaker to examine potential prosodic transfer effects. The data consisted of one controlled utterance, “Do you like noodles?”, produced by two female speakers (n = 2), both aged 25, to minimize biological variation in pitch range and voice quality. The recordings were elicited in a quiet environment and analyzed using Praat. The analysis focused on three acoustic parameters: fundamental frequency (F0) to represent intonation, intensity (in decibels), and total utterance duration (in seconds). Acoustic measurements were taken at the beginning and end of the utterance, and the results were compared descriptively. The findings show that the native English speaker produced a stable rising intonation pattern with increased intensity toward the end of the utterance and a shorter duration, which aligns with typical English yes/no question prosody. In contrast, the Javanese speaker exhibited a wider pitch range, decreasing intensity, and a slightly longer duration, suggesting the influence of Javanese prosodic patterns on English speech production. Although no statistical testing was conducted due to the limited sample size, the acoustic comparison provides preliminary insights into individual level prosodic variation. Pedagogically, the study highlights the usefulness of Praat as a visual and analytical tool to raise learners’ awareness of English intonation patterns and prosodic differences in second language pronunciation.
Formant analysis of single vowels in Mandarin spoken by Chinese female speakers Berutu, Elvi Jesica; Febrina, Wardani; Tengku Syarfina; Jelly Prima Silaban
International Journal of Culture and Art Studies Vol. 10 No. 1 (2026): International Journal of Culture and Art Studies (IJCAS)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/ijcas.v10i1.19873

Abstract

This study aimed to investigate the formant measurement of single vowel sounds in the Mandarin spoken by Chinese female speakers. This study employed the audio method. The data were collected from five Chinese female speakers after receiving instructions on the purpose of recording the Mandarin words ending in 7 distinct vowels: a[A], o[o], e[ɣ], ê[ɛ], i[i], u[u], and ü[y]. The audio were directly recorded into the computer, assigning a single file to each set of words from the sources. We used Praat software to extract the first (F1) and second (F2) formants from the data. Presenting the results in the form of numerical tables. The study's findings indicate a significant difference in their voice quality, despite the fact that they are all Chinese. Specifically, they produced the highest formant value for the single vowel [A] in the word "pà," and the longest duration for a Chinese female's pronunciation of the single vowel /o/ was 0.438750 seconds in the word "bo." Meanwhile, the pitch score was lowest for both native speakers and is found in the single vowel /u/ in the word 须 "Xue." The effect of pitch errors is one factor that affects the resulting formant and duration value.