Towards a domain-independent ASR-confidence classifier

Author(s):  
Om D. Deshmukh ◽  
Ashish Verma ◽  
Etienne Marcheret
Keyword(s):  
1998 ◽  
Vol 01 (02n03) ◽  
pp. 221-236 ◽  
Author(s):  
Diana Richards ◽  
Brendan D. McKay ◽  
Whitman A. Richards

The conditions under which the aggregation of information from interacting agents results in a stable or an unstable collective outcome is an important puzzle in the study of complex systems. We show that if a complex system of aggregated choice respects a mutual knowledge structure, then the prospects of a stable collective outcome are considerably improved. Our domain-independent results apply to collective choice ranging from perception, where an interpretation of sense data is made by a collection of perceptual modules, to social choice, where a group decision is made from a set of preferences held by individuals.


2011 ◽  
Vol 135-136 ◽  
pp. 573-577 ◽  
Author(s):  
Rui Shi Liang ◽  
Min Huang

Increasing interest has been devoted to Planning as Heuristic Search over the years. Intense research has focused on deriving fast and accurate heuristics for domain-independent planning. This paper reports on an extensive survey and analysis of research work related to heuristic derivation techniques for state space search. Survey results reveal that heuristic techniques have been extensively applied in many efficient planners and result in impressive performances. We extend the survey analysis to suggest promising avenues for future research in heuristic derivation and heuristic search techniques.


2017 ◽  
Vol 29 (7) ◽  
pp. 1119-1131 ◽  
Author(s):  
Katerina D. Kandylaki ◽  
Karen Henrich ◽  
Arne Nagels ◽  
Tilo Kircher ◽  
Ulrike Domahs ◽  
...  

While listening to continuous speech, humans process beat information to correctly identify word boundaries. The beats of language are stress patterns that are created by combining lexical (word-specific) stress patterns and the rhythm of a specific language. Sometimes, the lexical stress pattern needs to be altered to obey the rhythm of the language. This study investigated the interplay of lexical stress patterns and rhythmical well-formedness in natural speech with fMRI. Previous electrophysiological studies on cases in which a regular lexical stress pattern may be altered to obtain rhythmical well-formedness showed that even subtle rhythmic deviations are detected by the brain if attention is directed toward prosody. Here, we present a new approach to this phenomenon by having participants listen to contextually rich stories in the absence of a task targeting the manipulation. For the interaction of lexical stress and rhythmical well-formedness, we found one suprathreshold cluster localized between the cerebellum and the brain stem. For the main effect of lexical stress, we found higher BOLD responses to the retained lexical stress pattern in the bilateral SMA, bilateral postcentral gyrus, bilateral middle fontal gyrus, bilateral inferior and right superior parietal lobule, and right precuneus. These results support the view that lexical stress is processed as part of a sensorimotor network of speech comprehension. Moreover, our results connect beat processing in language to domain-independent timing perception.


Sign in / Sign up

Export Citation Format

Share Document