Effects of audio headings on learning.

Proceedings of the Human Factors and Ergonomics Society Annual

2020

Despite the prevalence of computer-generated speech, few studies have investigated the direct relationship between an agent’s voice and students’ perception or recall performance. This study investigated the effects of voice (without visual information) on students’ perception ratings and recall performance. Our results indicated that in the absence of visual information, students greatly preferred the human voice. The recall performance, however, indicated that the synthesized voices led to better recall performance. Implications for pedagogical practices are described in the discussion section.

Section: Materials and Proceduresmentioning

confidence: 99%

The Influence of Voice on Pedagogical Agent’s Persona and Recall Performance

Morris

Proceedings of the Human Factors and Ergonomics Society Annual

2020

“…Participants were presented with the cued recall and free recall questions on separate pages. The recall questions were adapted from a study by Chen and Lorch (2018). Participants could receive a maximum score of 6 points on the recall task, with three points possible for the cued recall questions and three points possible for the free recall questions.…”

Section: Materials and Proceduresmentioning

confidence: 99%

“…Modern voice engines may have advanced enough to do the job of the human voice in less stressful audio-only learning situations but have not advanced enough where they have reached equality or superiority to the human voice. Modern voice engines often are unable to translate signaling information, such as bold, italicized, or highlighted words, in the way the human voice can (Lorch et al, 2012;Chen & Lorch, 2018). The modern voice engine also lacks the inflection, cadence, and enunciation that the human voice has.…”

Section: Introductionmentioning

confidence: 99%

Voice’s Effect on Student Effort Ratings and Recall Performance While Under Cognitive Stress

Morris

Proceedings of the Human Factors and Ergonomics Society Annual

2021

Computer-generated speech is becoming more commonplace in classrooms, so it is important to examine the impact of computer voice on students’ cognition in a variety of learning situations. The current study investigated the effects of voice in a cognitively stressful, audio-only learning situation. In this experiment, 122 college students were recruited to listen to an audio lecture and respond to test questions. Our findings indicated that participants rated the classic voice engine as demanding the most effort and the human voice as demanding the least effort. Students also had the best recall performance in the human voice condition and the worst recall performance in the classic voice condition. Our results indicated that when learners are placed under cognitive stress, the human voice is the superior pedagogical agent. These results contribute to a growing body of research examining modern computer voice as a pedagogical agent.

“…In the Driving and Learning condition, participants had to answer eight free recall questions for a total of eight points. Participants' free recall performance was scored by four scorers using the scoring rubric adapted from the study by Chen and Lorch (2018). Scorers achieved 80% inter-rater reliability; subsequent scoring disagreements were resolved through discussion.…”

Section: Audio Learning-free Recall Performancementioning

confidence: 99%

“…Sessions 2 and 3 included two audio texts that were adapted from another study related to audio learning (Chen & Lorch, 2018). The audio files were generated by Amazon Kindle's text-to-speech engine from plain text format.…”

Section: Materials and Proceduresmentioning

confidence: 99%

Effects of Audio Learning on Semi-Autonomous Driving Safety

Proceedings of the Human Factors and Ergonomics Society Annual

Thomas

2020

Semi-autonomous driving has been found to require less cognitive resources from drivers. It is not immediately clear if engaging in secondary tasks such as audio learning is safe in a semi-autonomous driving situation, especially considering the finding that semi-autonomous drivers tend to be less engaged. The current study investigated the effects of audio learning during a simulated semi-autonomous driving situation. Our results indicated that audio learning could delay warning message reaction time, and drivers had worse audio learning performance in a simulated semi-autonomous driving situation. Implications of current findings on driver safety, audio learning, and forensic practices are described in the discussion section.