Usability of ASR-based reading training for dyslexics

Pedersen, Jakob Schou; Larsen, Lars Bo; Lindberg, Børge

doi:10.21437/interspeech.2008-474

Cited by 2 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the calibration the participant was given control of the mouse and began the reading session. Each participant read the same 23 short text segments of varying difficulty [1]. The experimenter was monitoring a live view of the eye-gaze tracking during each session and would tell the participant to adjust his or her position if the head had moved too far away from the optimal zone.…”

Section: Data Collection and Experiments Setupmentioning

confidence: 99%

“…It might also provide corrective feedback if the reader misreads a word. The feedback provided could be in the form of a picture (if possible), reading the word in question out loud, or a number of other ways [1]. It could also be a platform for reading assessment [2] or provide a speech driven interface to the reader [3].…”

Section: Introductionmentioning

confidence: 99%

“…At least three modalities can be used to this end: eye-gaze (or gaze), speech, and manual feedback requests. For example in [4] the authors use an eye-gaze tracker to provide assistance when the reader looks at a word for more than 360 msec and in [1], [2], and [3] the authors use automatic speech recognizers (ASR) in three different reading tutors. Manual requests for feedback can be done using the mouse; however, systems that provide this as the only way to get feedback fall in the category of interactive books rather than ART.…”

Section: Introductionmentioning

confidence: 99%

“…However, sometimes the reader returns to previously read words in order to revise or remember what was read. This is especially true for people with dyslexia who struggle with reading [1]. This means that an ART should be able to determine which word the reader is supposed to read next, in order to provide assistive feedback if necessary.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fusing eye-gaze and speech recognition for tracking in an automatic reading tutor – a step in the right direction?

Rasmussen,

Tan

2013

Speech and Language Technology in Education (SLaTE 2013)

View full text Add to dashboard Cite

In this paper we present a novel approach for automatically tracking the reading progress using a combination of eye-gaze tracking and speech recognition. The two are fused by first generating word probabilities based on eye-gaze information and then using these probabilities to augment the language model probabilities during speech recognition. Experimental results on a small dataset show that the tracking error rate of the system using only speech recognition is 34.9% whereas the tracking error rate for the system that incorporates eye-gaze tracking into the speech recognizer is 31.2% -a relative improvement of 10.6%.

show abstract

Section: Data Collection and Experiments Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fusing eye-gaze and speech recognition for tracking in an automatic reading tutor – a step in the right direction?

Rasmussen,

Tan

2013

Speech and Language Technology in Education (SLaTE 2013)

View full text Add to dashboard Cite

show abstract

“…The reading tutor can provide word-level assistance in a number of ways, e.g. by providing a visual representation of the word or by reading the word out loud [1]. Accurate tracking is important in order not to discourage the reader from using the system; if the system makes too many mistakes the reader will lose confidence in it.…”

Section: Introductionmentioning

confidence: 99%

Evaluating tracking accuracy of an automatic reading tutor

Rasmussen,

Mostow,

Tan

et al. 2011

Speech and Language Technology in Education (SLaTE 2011)

View full text Add to dashboard Cite

In automatic reading tutoring, tracking is the process of automatically following a reader through a given target text. When developing tracking algorithms, a measure of the tracking accuracy -how often a spoken word is aligned to the right target text word position -is needed in order to evaluate performance and compare different algorithms. This paper presents a framework for determining the observed tracking error rate. The proposed framework is used to evaluate three tracking strategies: A) follow the reader to whichever word he/she jumps to in the text, B) follow the reader monotonically from left to right ignoring word skips and regressions (going back to a previous text word), and C) the same as B but allowing isolated word skips. Observed tracking error rate for each of the three tracking strategies is:

show abstract

Usability of ASR-based reading training for dyslexics

Cited by 2 publications

References 0 publications

Fusing eye-gaze and speech recognition for tracking in an automatic reading tutor – a step in the right direction?

Fusing eye-gaze and speech recognition for tracking in an automatic reading tutor – a step in the right direction?

Evaluating tracking accuracy of an automatic reading tutor

Contact Info

Product

Resources

About