The current study concerns loanword accent of Nakijin Ryukyuan 1 , hereafter NR. NR, as well as many Japonic languages or dialects, has a pitch accent system. Kubozono (2006) and Kubozono & Giriko (2011) claim that in several Japanese dialects loanword accent is determined by two factors: perceptual similarity between L1 (a borrowing language such as Tokyo Japanese) and L2 (a borrowed language ...

It is well known that speaker variability caused by accent is an important factor in speech recognition. Some major accents in China are so different as to make this problem very severe. In this paper, we propose a Gaussian mixture model (GMM) based Mandarin accent identification method. In this method, a number of GMMs are trained to identify the most likely accent given test utterances. The i...

This study focuses on the word accent opposition in a lesser known and endangered variety of Swedish – Estonian Swedish. The variety has been described as not making the tonal distinction between Accent 1 and Accent 2 words, but no systematic acoustic phonetic investigation has been carried out previously to confirm these descriptions. As materials, disyllabic words from read sentences, spontan...

We present results from a series of 151 speech recognition experiments based on the N4 corpus of accented English speech, using a small vocabulary recognition system. These experiments looked at the impact of foreign accent on speech recognition, both within non-native accented English and across different accents, with particular interest in using context free grammar technology to improve cal...

The performance of speech recognition systems degrades when speaker accent is diierent from that in the training set. Accent-independent or accent-dependent recognition both require collection of more training data. In this paper, we propose a faster accent classiica-tion approach using phoneme-class models. We also present our ndings in acoustic features sensitive to a Cantonese accent, and po...

This study aimed to determine the relative processing cost associated with comprehension of an unfamiliar native accent under adverse listening conditions. Two sentence verification experiments were conducted in which listeners heard sentences at various signal-to-noise ratios. In Experiment 1, these sentences were spoken in a familiar or an unfamiliar native accent or in two familiar native ac...

In order to solve the problem of the performance decrease when state-of-art automatic speech recognition (ASR) system facing accent speech, we propose the Pronunciation Variation Model (PVM). Two approaches are proposed to construct the PVM in this paper. 6.38% and 7.78% relative error rate reduction is achieved for Shanghai and Wuhan accent mandarin, respectively. The experiment on these two t...

Evaluating the efficacy of accent transformation is important when localising speech-enabled software. However, perceived accent is an attribute assigned by a listener, and the apparent success of accent transformation will vary with the audience. Here we show the extent to which evaluations can be affected by audience familiarity with an accent. A perceptual study comparing two approaches to a...