Temporal Issues and Recognition Errors on the Capitalization of Speech Transcriptions

Abstract. This article explores the possibility of differentiating between patients suffering from Alzheimer’s disease (AD) and patients with other kinds of dementia by focusing on false alarms (FAs) on a picture recognition task (PRT). In Study 1, we compared AD and non-AD patients on the PRT and found that FAs discriminate well between these groups. Study 2 served to improve the discriminatory power of the FA score on the picture recognition task by adding associated pairs. Here, too, the FA score differentiated well between AD and non-AD patients, though the discriminatory power did not improve. The findings suggest that AD patients show a liberal response bias. Taken together, these studies suggest that FAs in picture recognition are of major importance for the clinical diagnosis of AD.

Download Full-text

Influence of Prior Paired-Associate Learning on False Recognition

Psychological Reports ◽

10.2466/pr0.1969.25.3.803 ◽

1969 ◽

Vol 25 (3) ◽

pp. 803-810 ◽

Cited By ~ 1

Author(s):

William P. Wallace

Keyword(s):

False Recognition ◽

Paired Associate ◽

Recognition Task ◽

Paired Associate Learning ◽

Major Portion ◽

Associate Learning ◽

Single Time ◽

Recognition Errors

Three experiments were reported which investigated transfer from paired-associate (PA) learning to a recognition task (RL). Exp. I demonstrated that learning a PA list of A-B associates increased recognition errors to B words in RL (B words occurred a single time late in RL and A words occurred early in RL). It was argued that the appearance of the A words elicited the B associates implicitly, and this led to increased difficulty in identifying B words as first occurrences. An attempt to decrease RL errors to B words by interpolating unlearning activities between the A-B list and RL were unsuccessful (Exp. II). Exp. III demonstrated that the major portion of the increased errors to B words following PA learning was due to general PA-RL confusion and that specific A-B elicitations during RL added only slightly to this general confusion.

Download Full-text

Characterizing and Predicting Corrections in Spoken Dialogue Systems

Computational Linguistics ◽

10.1162/coli.2006.32.3.417 ◽

2006 ◽

Vol 32 (3) ◽

pp. 417-438 ◽

Cited By ~ 19

Author(s):

Diane Litman ◽

Julia Hirschberg ◽

Marc Swerts

Keyword(s):

Speech Recognition ◽

Predictive Power ◽

Classification Error ◽

Dialogue Systems ◽

Dialogue System ◽

Spoken Dialogue Systems ◽

Experimental Conditions ◽

Spoken Dialogue ◽

Spoken Dialogue System ◽

Recognition Errors

This article focuses on the analysis and prediction of corrections, defined as turns where a user tries to correct a prior error made by a spoken dialogue system. We describe our labeling procedure of various corrections types and statistical analyses of their features in a corpus collected from a train information spoken dialogue system. We then present results of machine-learning experiments designed to identify user corrections of speech recognition errors. We investigate the predictive power of features automatically computable from the prosody of the turn, the speech recognition process, experimental conditions, and the dialogue history. Our best-performing features reduce classification error from baselines of 25.70–28.99% to 15.72%.

Download Full-text