In this paper we present the results obtained when evaluating the Natural Numbers Recognizer of Telefónica I+D over some particular dialects of Spanish from Spain and America. The evaluation was made over two different data sets corresponding to two different situations. A first set includes dialects of Spanish from Spain, that were considered in the training and design of our baseline system, ...

BACKGROUND/AIMS The current study explored the roles of dialect familiarityand social stereotypes in dialect interference effects in a speeded lexical classification task. METHODS Listeners classified the words bad and bed or had and head produced by local Midland and non-local Northern talkers and the words sod and side or rod and ride produced by non-local, non-stereotyped Northern and nonl...

Speech rhythm is highly variable. Previous studies reported variability between languages, dialects, speakers, and labelers. Research further revealed an effect of sentence in the rhythmic characteristics of speakers of the same language. In the present study we tested whether the effect of sentence material is constant across varieties of the same language. We addressed this question by an exa...

Several approaches to Chinese dialect identification based on segmental and prosodic features of speech are described in this paper. When using segmental information only, the system performs phonotactic analysis after speech utterances have been tokenized into sequences of broad phonetic classes. The second scheme comprises prosodic models which are trained to capture tone sequence information...

After carrying out field work on the Slavic dialects spoken in Greece, and more specifically in the village of Liti, I suggested the name Nashta “ours” for the dialect so as to respect the usage among the speakers and to emphasize the specific representation they have of their language. Of the Nashta syntactic features, I shall focus this work on the jimam perfect construction with the past pas...

Japanese dialects spoken in the Kinki and Shikoku regions have a lexical contrast of pitch register types called shiki. The shallow f0 downtrend in the high-pitched shiki type is thought of as a manifestation of backdrop f0 declination that is blind to tonal structure. Acoustic analysis of three Japanese dialects with 2or 3-way contrast of shiki types, however, reveals that the degree of f0 dec...

The ability to discern the use of a nonstandard dialect is often enough information to also determine the speaker’s ethnicity, and speakers may consequently suffer discrimination based on their speech. This article, detailing four experiments, shows that housing discrimination based solely on telephone conversations occurs, dialect identification is possible using the word hello, and phonetic c...

In this study, we tackle the question of pos-tagging written Occitan, a lesser-resourced language with multiple dialects each containing several varieties. For pos-tagging, we use a supervised machine learning approach, requiring annotated training and evaluation corpora and optionally a lexicon, all of which were prepared as part of the study. Although we evaluate two dialects of Occitan, Leng...

In daily communications, Arabs use local dialects which are hard to identify automatically using conventional classification methods. The dialect identification challenging task becomes more complicated when dealing with an under-resourced dialects belonging to a same county/region. In this paper, we start by analyzing statistically Algerian dialects in order to capture their specificities rela...