presentation劉思竹v4.2 10122608
TRANSCRIPT
1
The Effectiveness of Computer Assisted Pronunciation Training for Foreign
Language Learning by Children
Presenter: Sze-Chu Liu
Instructor: Dr. Pi-Ying Teresa Hsu
2102/10/15
2
Citation
Neri, A., Mich, O., Gerosa, M., & Giuliani, D.
(2008). The effectiveness of computer
assisted pronunciation training for foreign
language learning by children. Computer Assisted Language Learning, 21(5), 393-
408.
3
Introduction
The CAPT system considered: PARLING
Method
Results
Conclusions
Reflection
Outline
4
CAPT = Computer Assisted Pronunciation
Training
ASR = Automatic Speech Recognition
ITC-irst = Istituto Trentino di Cultura –
Istituto per la Ricerca Scientifica
e Tecnologica
Some Abbreviations
5
Pronunciation
training for
young
learners
Advantage
over adults
Accurate
perception
and
production
L1
acquisition
hampers L2
Introduction
6
Introduction
Typical FL
learning setting
Limited oral
exposure
Rare
interaction with
native speakers
The use of
computer
Abundant
spoken
examples
Self-paced
practice
7
Interactive
speech-based
games
Role-plays with
the computer
Automatic
feedback
Fun learning
experience
CAPT
with ASR
Introduction
8
Research questions
Is the effectiveness of CAPT systems for
children better than that of teach-led class?
Is CAPT able to help learners to learn
pronunciation of difficult words?
Introduction
9
The CAPT system considered: PARLING
Developed by ITC-irst
• Pronunciation quality
• Isolated word level
Providing automatic feedback
• Presentation of oscillograms
• Animated characters
Meeting the requirements
• Match traditional training
• Highlight pronouncing isolated words
10
The CAPT system considered: PARLING
The user interface of PARLING: 4 modules
11
The ASR component
The CAPT system considered: PARLING
Training Process
• Native British English speakers + Italian
learners of English
Recognization process
•Forced time-alignment likelihood (A)
•Phone recognition likelihood (B)
Decision making
• If A>B, respond “accept”; Otherwise,
“reject”
12
• Total: 28
• Control group: 15
• Experimental group: 13
Number of
samples
• 11-year-old Italian native speakers
• Same public school
• Same curriculum
Profile
• All had 4 years of English FL
classesBackground
Method
Participants
13
• 4 British teachersTeacher
• 4 sessions, 60 minutes for each
session
Schedule
• Hansel and Gretel (Englsh version)
• Printed handoutMaterial
•Teacher-led
•read
•explained
•Provided the correct
pronunciation
•Prompted to repeat aloud
•Played printed word game
Teaching
activities
Method
Training Procedure for Control Group
14
• Work with PARLINGTeacher
• 4 sessions, 30 minutes /sessionSchedule
• Hansel and Gretel (Englsih version)
• Story excerpt shown on screenMaterial
• Students-driven
• Listened and repeated
•Repeated a word until
permitted
• Played a word game
Teaching
activities
Method
Training Procedure for Experimental Group
15
Pre-test
Training
Procedure
Post-test
Method
Testing Procedure
Children read and record 28 isolated words
Recordings scored by 3 experts
The 28 words were classified as
easy (n = 21)/difficult (n = 7)
known (n = 21)/unknown (n = 7)
16
Method
Rating Procedure
Word #1
(e.g. away)
Word #2
(e.g. birds)
Word #28
S2S1 S28
Audio file #1
Audio file #2
Audio file #28
Speaker
#1
Speaker
#2
Speaker
#28
The pronunciation quality of each utterance is scored on a 10-point scale.
In total, each rater assigned 1656 scores.
17
Method
Table 1. Audio files scored by each rater
Single-word
scoresSpeaker scoresRater
reliability
18
Results
Reliability of ratings
Table 2. Reliability coefficients (Cronbach’s alpha)
These coefficients indicate high inter- and
intra- raters reliability.
19
Results
Single-word scores vs. Speaker scores
Figure 3. Correlation between single-word and speaker scores
A strong, positive
correlation between the two
scores (r = 0.884, p<0.01)
The speaker scores
were for the rest of
the analysis.
20
Results
Table 3. Pre-test and Post-test speaker scores for the two
groups
T-test results: t = .321, p = .754
Pronunciation quality is NOT significantly
different in the pre-test.
21
Results
Table 3. Pre-test and Post-test speaker scores
for the two groups
ANOVA #1: F(1,26) = 78.818, p <0.05
A significant effect for test time
indicated!
22
Results
Table 3. Pre-test and Post-test speaker scores
for the two groups
ANOVA #2: F(1,26) = 0.610, p = 0.442
Training group has NO significant
effect.
23
Results
Table 3. Pre-test and Post-test speaker scores
for the two groups
ANOVA #3: F(1,26)=0.548, p = .446
No significant test × training
interaction is found.
24
Results
Pronunciation quality of specific types of words
Difficult/Unknown Easy/Known
Mean SD Mean SD
Pre-test 3.06 1.10 5.11 1.08
Post-test 5.59 0.93 5.74 0.79
Over all 4.32 1.01 5.44 0.93
A significant effect is revealed for the
test.
ANOVA test #4: F(1,26) = 144.729, p < 0.01
25
Results
Pronunciation quality of specific types of words
Difficult/Unknown Easy/Known
Mean SD Mean SD
Pre-test 3.06 1.10 5.11 1.08
Post-test 5.59 0.93 5.74 0.79
Over all 4.32 1.01 5.44 0.93
A significant effect is shown for word
type.
ANOVA test #5: F(1,26) = 57.531, p < 0.01
26
Results
Pronunciation quality of specific types of words
Difficult/Unknown Easy/Known
Mean SD Mean SD
Pre-test 3.06 1.10 5.11 1.08
Post-test 5.59 0.93 5.74 0.79
Over all 4.32 1.01 5.44 0.93
A significant effect for word type is
indicated in the Pre-test.
ANOVA test #6: F(1,26 ) = 60.080, p < 0.01
27
The improvement in pronunciation quality
of isolated words in the two groups are
comparable.
The improvements in pronunciation quality
of difficult/unknown in the two groups are
comparable.
Conclusions
28
If the participants change to college
students, the material should be carefully
selected.
The improvement of pronunciation quality
at sentence level can be one direction for
future research.
The sample seems to be small.
Reflection
29
Thank you for listening!