Recent studies using behavioral measures of similarity between acoustic events have had interesting results, but have been inconclusive with regards to the basis on which event-class discrimination is made. In the present investigation, we suggest that much of the difficulty has resulted from confusion about the basis on which participants make similarity judgments. Judgments may well be made o...

The present study investigated the joint impact of target-flanker similarity and of spatial frequency content on the crowding effect in letter identification. We presented spatial frequency filtered letters to neurologically intact non-dyslexic readers while manipulating target-flanker distance, target eccentricity and target-flanker confusability (letter similarity metric based on published le...

Objective A great number of customers spend much more time than expected on shopping because of a lot of reasons like variety in products. Thus, they may feel confused and disappointed. Such confusion can influence purchasing procedure and determine purchasing behavior. Such customers fail to purchase wisely and may face difficulty choosing appropriate and reasonable products. However, if the ...

Tone merging and tonal confusion have been an interesting issue for a long time. This paper tries to investigate whether there is the phenomenon of merging tone in Hailu Hakka production. We focus on sandhi related tone pairs and level tone pairs. The results show that tone 24 and tone 33 is undergoing a sound change of merging in the younger speakers. It is proposed that both allophonic rules ...

A trademark is a mark used to identif​y various commodities. If same or similar trademark is registered for the same or similar commodity, the purchaser of the goods may be confused. Therefore, in the process of trademark registration examination, the examiner judges whether the trademark is the same or similar to the other applied or registered trademarks. ​The confusion in trademarks is ba...

Phone recognition experiments give information about the confusions between phones. Grouping the most confusable phones and making a multilevel hierarchical classification should improve phone recognition. In this paper a clustering method is investigated, based on phone confusion matrix, for the data-driven generation of phonetic broad classes (PBC) of the Portuguese language. The method is ba...

This paper proposes an efficient anti-keyword derivation method to improve the rejection performance of keyword spotting. In this method, each anti-keyword is derived from the large vocabulary lexicon considering acoustic similarity to keywords, making use of the confusion matrix. Experimental results show that a 3 % improvement of the rejection rate is obtained compared to conventional methods...

A confusion matrix (Kohavi and Provost, 1998) contains information about actual and predicted classifications done by a classification system. Performance of such systems is commonly evaluated using the data in the matrix. The following table shows the confusion matrix for a two class classifier. The entries in the confusion matrix have the following meaning in the context of our study: ● a is ...

This paper proposes a novel approach to automating the construction of transliterated-term lexicons. A simple syllable alignment algorithm is used to construct confusion matrices for cross-language syllable-phoneme conversion. Each row in the confusion matrix consists of a set of syllables in the source language that are (correctly or erroneously) matched phonetically and statistically to a syl...

Representing the true label as one-hot vector is common practice in training text classification models. However, representation may not adequately reflect relation between instance and labels, labels are often completely independent instances relate to multiple practice. The inadequate representations tend train model be over-confident, which result arbitrary prediction overfitting, especially...