A common technique to cope with the large variability in the acoustic realisations of the phonetic classes in speech, is to partition the data according to a linguistically significant variable. In this work, accent dependent phonetic models were trained and used both as an analysis tool for pronunciation variation and in the attempt to improve ASR performance. The Idea Accent dependent trainin...

This paper describes the data collection effort that is part of the project Sprekend Nederland (The Netherlands Talking), and discusses its potential use in Automatic Accent Location. We define Automatic Accent Location as the task to describe the accent of a speaker in terms of the location of the speaker and its history. We discuss possible ways of describing accent location, the consequence ...

This paper describes a method of automatic labeling of prosodic information focusing on accent types and accent phrase boundaries for Japanese spoken sentences. They are predicted by CRF (Conditional Random Fields) using linguistic information and F0 contour information. In the prediction of the accent type, we propose a method that uses a provisional accent type predicted by linguistic informa...

The accent system of Modern Japanese is characterized by patterns of high and low tones which are conventionally specified for each word, and words are grouped into several classes according to their accent patterns. Put differently, words belonging to the same class exhibit the same accent pattern. Some dialects, however, permit more than one accent patterns in the same class, which will be re...

We have developed the very first free online and free framework for teaching and learning Japanese prosody with features for word accent and phrase intonation. This framework is called OJAD (Online Japanese Accent Dictionary) [1], which provides three functions. 1) Visual, auditory, systematic, and comprehensive illustration of patterns of accent change (accent sandhi) of verbs and adjectives. ...

Toward the end of their first year of life, infants’ overly specified word representations are thought to give way to more abstract ones, which helps them to better cope with variation not relevant to word identity (e.g., voice and affect). This developmental change may help infants process the ambient language more efficiently, thus enabling rapid gains in vocabulary growth. One particular kin...

The authors investigated perceptual learning of a novel accent in young and older listeners through measuring speech reception thresholds (SRTs) using speech materials spoken in a novel-unfamiliar-accent. Younger and older listeners adapted to this accent, but older listeners showed poorer comprehension of the accent. Furthermore, perceptual learning differed across groups: The older listeners ...

We argue that phonetically invariant realizations of phonological categories imply the synchronic and diachronic imperviousness of such categories to phonological rules and sound laws. We claim that phonetic invariance is the foundation of phonological stability. The category we discuss in this contribution is the pitchaccent. We provide a parametric phonetic description of this phonological ca...

Five vowels /i, , æ, (or ), u/ in isolated /CVC/ words produced by 7 American English (AmE) and 6 Australian English (AusE) talkers were examined with a view to documenting acoustic-phonetic similarities and differences between the two accent types. The effect of Accent was significant on all vowels for at least one of the first two formants. The AusE vowel space was much more compressed relati...