Dialect variations of a language have a severe impact on the performance of speech systems. Therefore, knowing how close or separate dialects are in a given language space provides useful information to predict, or improve, system performance when there is a mismatch between train and test data. Distance measures have been used in several applications of speech processing, including speech reco...

This paper aims to design and implement speech recognition system with Discrete Wavelets transformation using Daubechies wavelets for analysis of continuous speech for similar sample sets. This work is based on analysis of Signals of Regional Dialects and finding similar pattern in the Regional Dialects of Demographic Region, which provides a highly reliable way for recognizing speech.The impor...

Dialect differences within a given language represent major challenges for sustained speech system performance. For speech recognition, little if any knowledge exists on differences between dialects (e.g. vocabulary, grammar, prosody, etc.). Effective dialect classification can contribute to improved ASR, speaker ID, and spoken document retrieval. This study, presents an approach to establish a...

The current study reports preliminary information gathered about First Nations English dialects in Canada and considers implications for speech-language pathology practice. Information was gathered from literature searches and forums of First Nations and non-First Nations speech-language pathologists, developmentalists, and linguists. The exploratory findings suggest that First Nations English ...

This project compares the accuracy of two automatic speech recognition (ASR) systems–Bing Speech and YouTube’s automatic captions–across gender, race and four dialects of American English. The dialects included were chosen for their acoustic dissimilarity. Bing Speech had differences in word error rate (WER) between dialects and ethnicities, but they were not statistically reliable. YouTube’s a...

Problem statement: In general, there are a number of rural dialects in Thai. However, four dialects are mainly spoken by Thai people residing in four core region including central, north, northeast and south regions. Recognizing and synthesizing Thai speech with different dialects are consequently difficult. Approach: Prosody is an important factor that must be taken into account, since the pro...

The present paper discusses the intonational features of 3 Swiss German dialects: Valais Swiss German (WS), representing the Alpine variety, and Zurich (ZH) and Berne (BE) Swiss German, representing the Midland dialects. By application of the Fujisaki intonation model, 24 speakers of the mentioned dialects are investigated according to their global as well as local intonational features. The BE...

Two studies provided direct support for a recently proposed dialect theory of communicating emotion, positing that expressive displays show cultural variations similar to linguistic dialects, thereby decreasing accurate recognition by out-group members. In Study 1, 60 participants from Quebec and Gabon posed facial expressions. Dialects, in the form of activating different muscles for the same ...

Models of intonation are typically based on one dialect and one style and do not account for interor intra-speaker variability. Speech data from the IViE corpus, however, demonstrate considerable variation in English intonation that occurs both across and within dialects (IViE = Intonational Variation in English, UK ESRC award R000237145, http://www.phon.ox.ac.k/~esther/ivyweb). In this paper, ...