The chapter begins with a brief summary of major findings of the current study, and the pedagogical implications with regard to English speaking skill development it carries. Subsequent to the limitations of the study, possible directions for future research are moderately addressed.
5.1 Brief Summary and Pedagogical Implications
In this study aiming at pinpointing problematic words to senior high school students and inspecting the interaction between people and technology, participants were asked to finish twenty exercises using the ASR system. Next, a post-treatment questionnaire was administered to all of the participants, ten of whom were further invited to share their attitudes and perceptions of the ASR technology through one-on-on interview. On the basis of the aforementione-on-oned elicited results, two main points are going to be made here.
First of all, in light of the high overlapping rate of difficult words detected by the ASR system and evaluated by human raters, it is suggested that teachers can trust the
system and give it a try. However, while using the system in speaking practices, teachers still need to pay attention to students’ individual needs since the response of the
questionnaire implied that learners desire to have a real instructor accompanying and
helping them locate the erroneous sounds specifically. Interestingly, on the other hand, some interviewees are worried about their nonnative-like pronunciation may puzzle the interlocutor and embarrass themselves, while others are much more anxious about whether they can make themselves understood in English. The latter group values the intelligibility issue more than their accuracy of articulation. Since it is hard for learners to master all these difficult sounds at home on their own, teachers might have to consider the possibility of step by step executing pronunciation instructions explicitly.
Second, according to the top 100 mispronounced words and its high overlapping rate with the basic 2000 vocabulary of junior high school, it can be concluded that EFL learners in Taiwan often learn English words without attending to its sound features.
Therefore, it is high time that we taught our students to learn the language holistically.
That is, the incorporation four skills into lectures should be valued. When exposed to a new word, learners are supposed to be encouraged to familiarize themselves with its acoustic information rather than simply focus on its form. Teachers can attempt to achieve the goal by firstly immersing learners in related audio materials, which will in turn elevate their listening competence. As one student said in the interview, “When I
finished each speaking exercise, I would play the model audio file and my own recorded file again to figure out where I made mistakes, but oftentimes I just can’t tell the
difference between my pronunciation and the that of model files.” Next, if time
permitting, the activity of dictogloss can also be implemented to enhance learners
listening and writing competences at the same time. Lastly, how to help learners while they’re “reading” articles is another issue to consider because one participant had mentioned in the interview, “When I’m reading the textbook articles, there would be a
breakdown if I stumble upon unfamiliar words to me. My flow of reading would be blocked whenever I encounter words I don’t know how to pronounce.” The hard-working student’s sincere distress indeed deserves much more attention and care and
manifests the significant role of pronunciation in language learning.
5.2 The Limitations and Future Research Directions
Since this is a small scale study, many aspects can be reconsidered and further improved. There are two major limitations of the present research that future investigations can work on. First is about the ASR system itself. Several participants have complained that they were unable to successfully submit their recorded files since the processing time was too long and the web would just crash, with the error rate being around five percent. That is, one student out of twenty reported the problem. This problem was then submitted to the website customer service but hasn’t been completely solved yet. Due to the deficiency, some diligent participants are eliminated from the present study. If the problem could be fixed, it would benefit more hard-working learners.
Besides, participants have made mention of their discoveries that if they conduct the exercise at a normal to high speech rate, the recognition result is often unsatisfying.
This is also where the teachers can help report to the ASR team in charge. In addition to the speech rate issue, the current ASR system actually can only deal with the erroneous pronunciation to the word-level. It would be better if the system can make improvement and help learners with their mispronunciation at the phoneme level. Based on the aforementioned discoveries, it is suggested that while applying the ASR system
of LearnMode to their speaking activities, teachers still need to spend some time examining learners’ audio files and help them further identify their phonemic problems.
The second issue is about the research design. Native speakers of English can be
invited to take part in the twenty exercises so as to examine whether the ASR system can accurately identify and highlight the “true errors” made by users. Also, native
speakers can also be recruited to be the human raters and provide more detailed comments and insights into learners’ speech output. As for the exercise items, they
could be trimmed and made short so the result given by the ASR can be more focused.
If the item can be shorter, then the result will present a far more authentic reflection on
specific sentence or words, rather than a general feedback on a bunch of sentences or paragraphs. What’s more, the instructor should be stricter on reminding participants of
keeping record of their findings in the learning logs after each exercise because it will
assist learners in raising their awareness of the problematic pronunciations, and if
possible, establishing their learner autonomy to do the self-correction in the meantime.
“I find it very interesting to do the exercise, and it builds my confidence in speaking English,” “I always look forward to try new challenges and see the recognition
result that AI robot generates,” recounted happily by two low achiever interviewees.
From their sincere words, it was apparent that English speaking definitely matters to them even though they may not have good academic performance. The ASR technologies can benefit our learners and help them speak up in the world with powerful voice if teachers can judiciously incorporate it into instruction and transform the traditional EFL teaching scenarios.
REFERENCES
Ahn, T. Y., & Lee, S. M. (2016). User experience of a mobile speaking application with automatic speech recognition for EFL learning. British Journal of Educational Technology, 47(4), 778-786.
Ali, S. (2016). Towards the development of a comprehensive pedagogical framework for pronunciation training based on adapted automatic speech recognition systems. In EUROCALL 2016: COMMUNITIES AND CULTURE.
Research-publishing. net.
Anthony, L. (2019). AntConc (Version 3.5.8) [Computer Software]. Tokyo, Japan:
Waseda University. Available from
https://www.laurenceanthony.net/software
Ashwell, T., & Elam, J. R. (2017). How Accurately Can the Google Web Speech API Recognize and Transcribe Japanese L2 English Learners' Oral Production?.
Jalt Call Journal, 13(1), 59-76.
Bernstein, J., & Franco, H. (1996). Speech recognition by computer. Principles of experimental phonetics. St. Louis: Mosby.
Bueno Alastuey, M. C. (2011). Perceived benefits and drawbacks of synchronous voice-based computer-mediated communication in the foreign language classroom. Computer Assisted Language Learning, 24(5), 419-432.
Chen, A.-H. (2012). Exploring the effectiveness of reinforcing pronunciation training, spoken language. In Proceedings from CALL 2012: 15th International CALL Conference – The Medium Matters (pp. 110–112), Taichung:
Providence University.
Celce-Murcia, Marianne, Donna Brinton and Janet M. Goodwin. (1996). Teaching pronunciation: A reference for teachers of English to speakers of other languages. Cambridge: Cambridge University Press.
Chen, H. H. J. (2001). Evaluating five speech recognition programs for ESL learners.
Papers from the ITMELT 2001 Conference.
Chen, H. H. J. (2004). Automatic speech recognition and oral proficiency assessment.
In Proceedings of International Conference on English Language Teaching Instruction and Assessment (pp. 85-102).
Chen, H. H. J. (2011). Developing and evaluating an oral skills training website supported by automatic speech recognition technology. ReCALL, 23(1), 59-78.
Chen, H. H. J. (2017). Developing a Speaking Practice Website by Using Automatic Speech Recognition Technology. In: Wu TT., Gennari R., Huang YM., Xie H., Cao Y. (eds) Emerging Technologies for Education. SETE 2016. Lecture
Notes in Computer Science, vol 10108. Springer, Cham
Chen, H. H. J., & Chen, L. W. C. (2018). Automated Speech Assessment. The TESOL Encyclopedia of English Language Teaching, 1-6.
Chen K. T. (2004). An Investigation on the Impact of ASR Software Feedback on EFL College Students' Pronunciation Learning
Chiu, T.-L., Liou, H.-C., & Yeh, Y. (2007). A study of web-based oral activities enhanced by automatic speech recognition for EFL college learning.
Computer Assisted Language Learning, 20, 209–233.
Cordier, D. (2009). Speech recognition software for language learning: Toward an evaluation of validity and student perceptions.
Derwing, T. M., & Munro, M. J. (2015). Pronunciation fundamentals: Evidence-based perspectives for L2 teaching and research (Vol. 42). John Benjamins
Publishing Company.
Ehsani, F. & Knodt, E. (1998). Speech Technology in Computer-Assisted Language Learning: Strengths and Limitations of a New CALL Paradigm. Language Learning & Technology, 2(1), 45-60.
Elimat, A. K., & AbuSeileek, A. F. (2014). Automatic speech recognition technology as an effective means for teaching pronunciation. JALT CALL Journal, 10(1), 21-47.
Eskénazi, M. (1999) "Using a Computer in Foreign Language Pronunciation Training:
What Advantages?", Tutors that Listen: Speech Recognition for Language Learning, Special Issue, CALICO Journal 16, 3: 447-469.
Gaida, C., Lange, P., Petrick, R., Proba, P., Malatawy, A., & Suendermann-Oeft, D.
(2014). Comparing open-source speech recognition toolkits. Tech. Rep., DHBW Stuttgart.
Gilakjani, A. P. (2012). The Significance of Pronunciation in English Language Teaching. English Language Teaching, 5(4), 96-108.
Golonka, E., Bowles, A., Frank, V., Richardson, L. & Freynik, S. (2012).
Technologies for foreign language learning: a review of technology types and their effectiveness. Computer Assisted Language Learning, 1-36.
http://www2.elc.polyu.edu.hk/conference/papers2001/chen.htm.
Hincks, R. (2003). Speech technologies for pronunciation feedback and evaluation.
ReCALL, 15(1), 3-20.
Hsu, L. (2016). An empirical examination of EFL learners' perceptual learning styles and acceptance of ASR-based computer-assisted pronunciation training.
Computer Assisted Language Learning, 29(5), 881-900.
Kelly, G. (2000). How to teach pronunciation. Harlow, U.K.: Longman.
Kim, I. S. (2006). Automatic speech recognition: Reliability and pedagogical
implications for teaching pronunciation. Educational Technology & Society, 9(1), 322-334.
Kimura, T. (2013). Improvement of EFL learners’ speaking proficiency with a web-based CALL system. Glasgow WorldCall Papers, 141.
Levis, J., & Suvorov, R. (2012). Automatic speech recognition. The encyclopedia of applied linguistics.
Lin, C. Y. (2014). Perception and Production of Five English Front Vowels by College Students. English Language Teaching, 7(9), 14-20.
Liu, Q. (2011). Factors Influencing Pronunciation Accuracy: L1 Negative Transfer, Task Variables and Individual Aptitude. English Language Teaching, 4(4), 115-120.
Luo, B. (2016). Evaluating a computer-assisted pronunciation training (CAPT) technique for efficient classroom instruction. Computer Assisted Language Learning, 29(3), 451-476.
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.
Neri, A., Cucchiarini, C., & Strik, H. (2003, August). Automatic speech recognition for second language learning: how and why it actually works. In Proc.
ICPhS (pp. 1157-1160).
O’Brien, M. G., Derwing, T. M., Cucchiarini, C., Hardison, D. M., Mixdorff, H., Thomson, R. I., ... & Levis, G. M. (2018). Directions for the future of technology in pronunciation research and teaching. Journal of Second Language Pronunciation, 4(2), 182-207.
Pourhosein Gilakjani, A., & Sabouri, N. B. (2017). Advantages of using computer in teaching English pronunciation. International Journal of Research in English Education, 2(3), 78-85.
Precoda, K., & Bratt, H. (2008). Perceptual underpinnings of automatic pronunciation assessment. The path of speech technologies in computer assisted language learning, 71-84.
Radant, H. L. H. J., & Huang, H. L. (2009). Chinese phonotactic patterns and the pronunciation difficulties of Mandarin-Speaking EFL learners. The Asian EFL Journal Quarterly December 2009 Volume 11, Issue 4, 148.
Saito, K. (2007). The influence of explicit phonetic instruction on pronunciation in EFL settings: The case of English vowels and Japanese learners of English.
Linguistics Journal, 2(3), 16-40.
Saito, K. (2014). Experienced teachers' perspectives on priorities for improved intelligible pronunciation: The case of J apanese learners of E nglish.
International Journal of Applied Linguistics, 24(2), 250-277.
Teng, Hsin-yi. (2002). Chinese Students’ Performance in the Pronunciation of English Tense and Lax Vowels. Unpublished MA thesis, National Taiwan Normal University.
Oliveros, J.C. (2007-2015) Venny. An interactive tool for comparing lists with Venn's diagrams. https://bioinfogp.cnb.csic.es/tools/venny/index.html
Wang, Y. H., Young, S.S.C. (2014). A study of the design and implementation of the ASR-based iCASL system with corrective feedback to facilitate English learning. Educ. Technol. Soc. 17(2), 219–233
Warren. J. (2012). The Effects of Automatic Speech Recognition and Text-to-speech Software on EFL Students' Pronunciation. Available from
https://hdl.handle.net/11296/xbau3q
Zielinski, B. (2019). The Segmental/ Suprasegmental Debate. The handbook of English pronunciation, 397.