Vowels and tones as acoustic cues in Chinese subregional dialect identification

Liu, Huangmei; Liang, Jie; Heuven, Vincent J. van; Heeringa, Wilbert

doi:10.1016/j.specom.2020.06.006

Cited by 4 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, those research works necessitate the hand-crafted extraction of formant1 (F1) and formant2 (F2), which presents significant challenges due to the large amount of data and speaker acoustic variation. This work differs from previous studies that used Praat with phonetics principles in the analysis of pronunciation [12][13][14][15][16][17]. In general practice, linguists usually employ the F1 and F2 using Praat.…”

Section: Thai Vowels [This Work]mentioning

confidence: 90%

“…In order to accurately recognize pronunciations, there are many tasks that use specific techniques or special tools to analyze them, for example, developing a 3D pronunciation learning system in Chinese [9], using ultrasound with the pronunciation of consonants [10], developing an application that helps to analyze tones in Thai [11], and applying the Praat program for analyzing phonetics to demonstrate the pronunciation of vowels [12][13][14][15][16][17].…”

Section: Contributions In Automatic Thai Vowels Pronunciation Recogni...mentioning

confidence: 99%

See 1 more Smart Citation

An Acoustic Feature-Based Deep Learning Model for Automatic Thai Vowel Pronunciation Recognition

Rukwong

Pongpinigpinyo

2022

Applied Sciences

View full text Add to dashboard Cite

For Thai vowel pronunciation, it is very important to know that when mispronunciation occurs, the meanings of words change completely. Thus, effective and standardized practice is essential to pronouncing words correctly as a native speaker. Since the COVID-19 pandemic, online learning has become increasingly popular. For example, an online pronunciation application system was introduced that has virtual teachers and an intelligent process of evaluating students that is similar to standardized training by a teacher in a real classroom. This research presents an online automatic computer-assisted pronunciation training (CAPT) using deep learning to recognize Thai vowels in speech. The automatic CAPT is developed to solve the inadequacy of instruction specialists and the complex vowel teaching process. It is a unique system that develops computer techniques integrated with linguistic theory. The deep learning model is the most significant part of recognizing vowels pronounced for the automatic CAPT. The major challenge in Thai vowel recognition is the correct identification of Thai vowels when spoken in real-world situations. A convolutional neural network (CNN), a deep learning model, is applied and developed in the classification of pronounced Thai vowels. A new dataset for Thai vowels was designed, collected, and examined by linguists. The result of an optimal CNN model with Mel spectrogram (MS) achieves the highest accuracy of 98.61%, compared with Mel frequency cepstral coefficients (MFCC) with the baseline long short-term memory (LSTM) model and MS with the baseline LSTM model have an accuracy of 94.44% and 90.00% respectively.

show abstract

Section: Thai Vowels [This Work]mentioning

confidence: 90%

Section: Contributions In Automatic Thai Vowels Pronunciation Recogni...mentioning

confidence: 99%

An Acoustic Feature-Based Deep Learning Model for Automatic Thai Vowel Pronunciation Recognition

Rukwong

Pongpinigpinyo

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Tone duration was defined as the time interval between the first and the third points, the extreme time values. Such quantification methods for tones were proved to be capable of maintaining tonal information well (Liu et al, 2020 , in press). The quantification method is based on Chao's ( 1930 ) impressionistic description method for Mandarin tones and proposes that three points are enough to describe a tone.…”

Section: Methodsmentioning

confidence: 99%

“…Strictly speaking, an official dialect has no native speakers but is spoken by a large number of speakers of various regional dialects. Thus, as a consequence of the coevolution of official dialects and local dialects, there is a certain number of regional variants of an official dialect (Liu et al, 2020 ). Therefore, how regional natives perceive and describe the variants of an official dialect is a source of the coevolution of the official and regional dialects in a local region.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effects of Familiarity and Dialect Experience on the Description of Tonal Variant

Liu

Gibbon

2022

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

This study investigates the tonal variant description of the official dialect in China (Putonghua) as a factor in the coevolution of dialects. Three sociophonetic factors, target tone familiarity, tonal variant familiarity, and tonal inventory size, are included in order to raise interesting theoretical questions concerning the role of familiarity and dialect experience in sound change. Standard Putonghua tones are manipulated in height and shape in order to create systematically varying stimuli. Speakers from three Chinese dialect groups, Beijing Mandarin, Shanghai Wu, and Guangzhou Cantonese, are invited to rate the applicability of a description of pitch contour and height to the stimuli. The three dialects have different tonal inventory size, and their native speakers have different levels of familiarity with Putonghua tone or Putonghua tonal variants. The above three sociophonetic factors make different predictions about listeners' performances. The findings of the experimental analysis of data confirm the role of tonal variant familiarity in predicting participants' descriptive decisions on tone height variants. Tonal variant familiarity is also combined with tone inventory size to explain the assignment of descriptions of tone shape variations. This suggests that when variations still follow the phonetic pattern of the tone distribution of the Putonghua tonal system, listeners give phonetic patterns the primary role in acoustic decisions but still benefit from their dialect experiences in making more precise acoustic decisions. It also suggests that when variations violate the phonetic features of the target tonal system, they may depend on familiarity with the individual variant. This study applies an innovative sociophonetic method by conducting a perception experiment online with a self-paced procedure. The findings here are crucial for examining the relationship between sociophonetic factors and listeners' acoustic decisions and the cultural coevolution of cross-dialect tonal variation. The findings here also give support to the validity of the current web-based crowd perception experiment design and are also needed to facilitate research under restricted conditions, such as a pandemic situation.

show abstract

Dialect Identification using Chroma-Spectral Shape Features with Ensemble Technique

Chittaragi

Koolagudi

2021

Computer Speech & Language

View full text Add to dashboard Cite

Vowels and tones as acoustic cues in Chinese subregional dialect identification

Cited by 4 publications

References 20 publications

An Acoustic Feature-Based Deep Learning Model for Automatic Thai Vowel Pronunciation Recognition

An Acoustic Feature-Based Deep Learning Model for Automatic Thai Vowel Pronunciation Recognition

Effects of Familiarity and Dialect Experience on the Description of Tonal Variant

Dialect Identification using Chroma-Spectral Shape Features with Ensemble Technique

Contact Info

Product

Resources

About