Improving Mispronunciation Detection of Mandarin Tones for Non-Native Learners With Soft-Target Tone Labels and BLSTM-Based Deep Tone Models

2019 ◽  
Vol 27 (12) ◽  
pp. 2012-2024 ◽  
Author(s):  
Wei Li ◽  
Nancy F. Chen ◽  
Sabato Marco Siniscalchi ◽  
Chin-Hui Lee
Author(s):  
Yuxia Wang ◽  
Xiaohu Yang ◽  
Hongwei Ding ◽  
Can Xu ◽  
Chang Liu

Purpose The purpose of this study was to examine the aging effects on the categorical perception (CP) of Mandarin lexical Tones 1–4 and Tones 1–2 in noise. It also investigated whether listeners' categorical tone perception in noise correlated with their general tone identification of 20 natural vowel-plus-tone signals in noise. Method Twelve younger and 12 older listeners with normal hearing were recruited in both tone identification and discrimination tasks in a CP paradigm where fundamental frequency contours of target stimuli varied systematically from the flat tone (Tone 1) to the rising/falling tones (Tones 2/4). Both tasks were conducted in quiet and noise with signal-to-noise ratios set at −5 and −10 dB, respectively, and general tone identification of natural speech signals was also tested in noise conditions. Results Compared with younger listeners, older listeners had shallower identification slopes and smaller discrimination peakedness in Tones 1–2/4 perception in all listening conditions, except for Tones 1–4 perception in quiet where no group differences were found. Meanwhile, noise affected Tones 1–2/4 perception: The signal-to-noise ratio condition at −10 dB brought shallower slope in Tones 1–2/4 identification and less peakedness in Tones 1–4 discrimination for both listener groups. Older listeners' CP in noise, the identification slopes in particular, positively correlated with their general tone identification in noise, but such correlations were partially missing for younger listeners. Conclusions Both aging and the presence of speech-shaped noise significantly reduced the CP of Mandarin Tones 1–2/4. Listeners' Mandarin tone recognition may be related to their CP of Mandarin tones.


2017 ◽  
Vol 26 (1) ◽  
pp. 18-26 ◽  
Author(s):  
Yuxia Wang ◽  
Xiaohu Yang ◽  
Hui Zhang ◽  
Lilong Xu ◽  
Can Xu ◽  
...  

Purpose The purpose of the study was to examine the aging effect on the categorical perception of Mandarin Chinese Tone 2 (rising F0 pitch contour) and Tone 3 (falling-then-rising F0 pitch contour) as well as on the thresholds of pitch contour discrimination. Method Three experiments of Mandarin tone perception were conducted for younger and older listeners with Mandarin Chinese as the native language. The first 2 experiments were in the categorical perception paradigm: tone identification and tone discrimination for a series of stimuli, the F0 contour of which systematically varied from Tone 2 to Tone 3. In the third experiment, the just-noticeable differences of pitch contour discrimination were measured for both groups. Results In the measures of categorical perception, older listeners showed significantly shallower slopes in the tone identification function and significantly smaller peakedness in the tone discrimination function compared with younger listeners. Moreover, the thresholds of pitch contour discrimination were significantly higher for older listeners than for younger listeners. Conclusion These results suggest that aging reduced the categoricality of Mandarin tone perception and worsened the psychoacoustic capacity to discriminate pitch contour changes, thereby possibly leading to older listeners' difficulty in identifying Tones 2 and 3.


2018 ◽  
Vol 101 ◽  
pp. 1-10 ◽  
Author(s):  
Peggy Pik Ki Mok ◽  
Albert Lee ◽  
Joanne Jingwen Li ◽  
Robert Bo Xu
Keyword(s):  

2011 ◽  
Vol 474-476 ◽  
pp. 1049-1052
Author(s):  
Tian Guan ◽  
Qin Gong ◽  
Tong Zhou

In order to improve the pitch perception of cochlear implant (CI) users speaking tonal language, it has been suggested to frequency-modulate the electric stimulus rate by the spectral information of the tonal language. A piecewise CI rate modulation strategy has been recently proposed, which not only encoded the spectral information but also took account of the psychological perception feature for the stimulus rate variation by CI users. This paper further examines its performance to convey Mandarin tonal information by a neural-network-based simulation. The experimental results shown that the correct rates to identify the four Mandarin tones of 80 Mandarin monosyllabic words were 95%, 95%, 100% and 100%, respectively, indicating that the piecewise rate modulation strategy might efficiently convey Mandarin tonal information. Therefore, the piecewise rate modulation strategy could help to design novel CI electric stimulator and enhance the speech perception ability of CI users speaking tonal language, such as Mandarin.


Sign in / Sign up

Export Citation Format

Share Document