The effectiveness of computer-based speech corrective feedback for improving segmental quality in L2 Dutch

Abstract

Although the success of automatic speech recognition (ASR)-based Computer Assisted Pronunciation Training (CAPT) systems is increasing, little is known about the pedagogical effectiveness of these systems. This is particularly regrettable because ASR technology still suffers from limitations that may result in the provision of erroneous feedback, possibly leading to learning breakdowns. To study the effectiveness of ASR-based feedback for improving pronunciation, we developed and tested a CAPT system providing automatic feedback on Dutch phonemes that are problematic for adult learners of Dutch. Thirty immigrants who were studying Dutch were assigned to three groups using either the ASR-based CAPT system with automatic feedback, a CAPT system without feedback, or no CAPT system. Pronunciation quality was assessed for each participant before and after the training by human experts who evaluated overall segmental quality and the quality of the phonemes addressed in the training. The participants' impressions of the CAPT system used were also studied through anonymous questionnaires. The results on global segmental quality show that the group receiving ASR-based feedback made the largest mean improvement, but the groups' mean improvements did not differ significantly. The group receiving ASR-based feedback showed a significantly larger improvement than the no-feedback group in the segmental quality of the problematic phonemes targeted.

Evaluating a computer-assisted pronunciation training (CAPT) technique for efficient classroom instruction

“…However, the software used by Anderson-Hsieh (1994), Hirata (2004), or Tanner and Landon (2009) is unsuitable for correcting segmental errors. Neri, Cucchiarini, and Strik (2008) reported that students who used a CAPT system with a simple ASR component demonstrated improved pronunciation quality of isolated words equal to that of students who only received in-class instruction. Learners in the Hirata (2004) study improved their production not only in word-in-isolation but also in word-in-sentence contexts, while Cheng (1998) and AbuSeileek (2007) both reported that the use of meaningful text was more effective than unreal words or nonsense texts.…”

Using Intelligent Personal Assistants for Second Language Learning: A Case Study of Alexa

“…Despite the positive results found in these studies, ASR‐based systems do not always outperform traditional teacher‐led training. A study with L2 Dutch learners by Neri, Cucchiarini, and Strik () found that there were no significant differences in pronunciation improvements between the CAPT group and the control group. The researchers posited that intensified training combined with a more targeted system catering to speakers of the same language could have led to greater gains among the students using CAPT.…”

Advantages of Using Computer in Teaching English Pronunciation

“…The results revealed that subjects who used Rosetta Stone software had a significant improvement in the quality of their pronunciation while those who used traditional instruction did not have any pronunciation improvement. Neri, Cucchiarini, and Strik (2008) examined the effect of ASR software on pronunciation. The findings showed that the Email: info@ijreeonline.com group who received feedback from ASR software had a greater pronunciation improvement than the group who did not receive any feedback on the segmental quality of the difficult phonemes.…”