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...

This research investigates dialectal variations of the pitch accent system in Korean. Specifically, this paper is focused on how speakers of a nonlexical pitch accent dialect are influenced by a lexical pitch accent dialect. Three experiments have participants from two dialectal regions produce pitch accent minimal pairs, and imitate and identify continua spanning pitch accent categories. Resul...

We propose a multi-accent deep neural network acoustic model with an accent-specific top layer and shared bottom hidden layers. The accent-specific top layer is used to model the distinct accent specific patterns. The shared bottom hidden layers allow maximum knowledge sharing between the native and the accent models. This design is particularly attractive when considering deploying such a syst...

A method of modelling accent-specific pronunciation variations is presented. Speech from an unseen accent group is phonetically transcribed such that pronunciation variations may be derived. These context-dependent variations are clustered in a decision tree which is used as a model of the pronunciation variation associatedwith this new accent group. The tree is then used to build a new pronunc...

In this study, we examined the influence of an Alaska Native (AN) accent and reputation on perceived therapist credibility after controlling for universal-diverse orientation. Participants listened to and rated therapist audio recordings that differed in AN accent (strong, minimal) and reputational cues (expert, recent graduate, student). While credibility ratings of the accent conditions did n...

Based on results from psycholinguistic and neurolinguistic research on the perception of word accents in Central Swedish, we argue that Accent 2 could be seen as “marked,” as opposed to the unmarked Accent 1. The markedness of Accent 2 is assumed to be both phonetic, due to its relatively more complex high tone, and cognitive, due to the fact that the Accent 2 tone activates more word forms and...

This chapter deals with the typology of word prosodic systems and, specifically, discusses the notion ‘pitch-accent (language)’, asking whether there is such a class of languages as distinct from the notions ‘stress (language)’ and ‘tone (language)’. Several issues will turn out to be crucial. Firstly, there is the issue of recognizing (or not) a notion of accent which could be said to underlie...