scholarly journals Towards a New Methodology to Capture the Legal Compatibility of Conversational Speech Agents

Author(s):  
Ernestine Dickhaut ◽  
Laura Friederike Thies ◽  
Andreas Janson ◽  
Alexander Roßnagel ◽  
Jan Marco Leimeister
1995 ◽  
Vol 4 (3) ◽  
pp. 39-46 ◽  
Author(s):  
Susan K. Rafaat ◽  
Susan Rvachew ◽  
Rebecca S. C. Russell

Pairs of speech-language pathologists independently rated severity of phonological impairment for 45 preschoolers, aged 30 to 65 months. Children were rated along a continuum from normal to profound. In addition to judging overall severity of impairment, the clinicians provided separate ratings based on citation form and conversational samples. A judgment of intelligibility of conversational speech was also required. Results indicated that interclinician reliability was adequate (80% agreement) for older preschool-aged children (4-1/2 years and above) but that judgments by speechlanguage pathologists were not sufficiently reliable for children under 3-1/2 years of age 40% agreement). Children judged to have age appropriate phonological abilities were not clearly distinguishable from children judged to have a mild delay. Educating speech-language pathologists regarding the normative phonological data that are available with respect to young preschoolers, and ensuring that such data are readily accessible for assessment purposes, is required.


Author(s):  
Kyu Han ◽  
Akshay Chandrashekaran ◽  
Jungsuk Kim ◽  
Ian Lane

Author(s):  
Cenk Demiroglu ◽  
Aslı Beşirli ◽  
Yasin Ozkanca ◽  
Selime Çelik

AbstractDepression is a widespread mental health problem around the world with a significant burden on economies. Its early diagnosis and treatment are critical to reduce the costs and even save lives. One key aspect to achieve that goal is to use technology and monitor depression remotely and relatively inexpensively using automated agents. There has been numerous efforts to automatically assess depression levels using audiovisual features as well as text-analysis of conversational speech transcriptions. However, difficulty in data collection and the limited amounts of data available for research present challenges that are hampering the success of the algorithms. One of the two novel contributions in this paper is to exploit databases from multiple languages for acoustic feature selection. Since a large number of features can be extracted from speech, given the small amounts of training data available, effective data selection is critical for success. Our proposed multi-lingual method was effective at selecting better features than the baseline algorithms, which significantly improved the depression assessment accuracy. The second contribution of the paper is to extract text-based features for depression assessment and use a novel algorithm to fuse the text- and speech-based classifiers which further boosted the performance.


2001 ◽  
Vol 16 (5) ◽  
pp. 345-351 ◽  
Author(s):  
Hugo R. van Dongen ◽  
Philippe F. Paquier ◽  
Wouter L. Creten ◽  
John van Borsel ◽  
Coriene E. Catsman-Berrevoets

Author(s):  
Joanne E. Roberts ◽  
Elizabeth A. Hennon ◽  
Johanna R. Price ◽  
Elizabeth Dear ◽  
Kathleen Anderson ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document