It is notoriously difficult to evaluate L2 prosody objectively, since there is little consensus as to what constitutes a correct prosody for a given utterance. This presentation describes an automatic procedure which consists in comparing a non-native speakers production with 10 instances of the same utterance, taken from the OMProDat database, and read by native speakers. The pitch and relativ...

In this paper we present a novel technique for combining a Speaker Verification System with an Utterance Verification System in a Speaker Authentication system over the telephone. Speaker Verification consists in accepting or rejecting the claimed identity of a speaker by processing samples of his/her voice. Usually, these systems are based on HMM's that try to represent the characteristics of ...

Computer Assisted Language Learning (CALL) applications for improving the oral skills of low-proficient learners have to cope with nonnative speech that is particularly challenging. Since unconstrained nonnative ASR is still problematic, a possible solution is to elicit constrained responses from the learners. In this paper we describe experiments aimed at selecting utterances from lists of res...

A dedicated resource, consisting of annotated speech data, tools, and workflow design, was developed for the detailed investigation of discourse phenomena in Taiwan Mandarin. The discourse phenomena have functions which are associated with positions in utterances, and temporal properties, and include discourse markers (‘NAGE’, ’NA’, e.g. ‘hesitation’, ‘utterance initiation’), discourse particle...

There are many respects in which the conventional content of an utterance reflects speaker assumptions about the context of utterance and the relation between that context and the intended interpretation of the utterance. Taken together, these constitute what Vallduví (1992,1993) called the Information Packaging of the utterance, aka its Information Structure. Two central aspects of this Inform...

We develop a method to detect erroneous interpretation results of user utterances by exploiting utterance histories of individual users in spoken dialogue systems that were deployed for the general public and repeatedly utilized. More specifically, we classify barge-in utterances into correctly and erroneously interpreted ones by using features of individual users’ utterance histories such as t...

Research on the analysis of counselling conversations through natural language processing methods has seen remarkable growth in recent years. However, potential this field is still greatly limited by lack access to publicly available therapy dialogues, especially those with expert annotations, but it been alleviated thanks release AnnoMI, first and freely conversation dataset 133 faithfully tra...

A significant amount of speech is typically required for speaker verification system development and evaluation, especially in the presence of large intersession variability. This paper introduces a source and utterance-duration normalized linear discriminant analysis (SUN-LDA) approaches to compensate session variability in short-utterance i-vector speaker verification systems. Two variations ...

The goal of the work presented here is to automatically predict the type of an utterance in spoken dialogue by using automatically extracted suprasegmental information. For this task, we present and compare three stochastic algorithms: hidden Markov models, artificial neural nets, and classification and regression trees. These models are easily trainable, reasonably robust and fit into the prob...