This paper describes a mechanism for identifying errors made by a student during a computer-aided language learning dialogue. The mechanism generates a set of ‘perturbations’ of the student’s original typed utterance, each of which embodies a hypothesis about an error made by the student. Perturbations are then passed through the system’s ordinary utterance interpretation pipeline, along with t...

AIM Acoustic characteristics associated with varied utterance positions were examined to understand the acoustic consequences of potential articulatory changes near utterance boundaries. METHODS Second formant transition characteristics, including transition duration (ms), transition extent (Hz), and derived slope of transition (Hz/ms), of 12 healthy speakers of American English were examined...

Children's early productions are highly variable. Findings from children's early productions of grammatical morphemes indicate that some of the variability is systematically related to segmental and phonological factors. Here, we extend these findings by assessing 2-year-olds' production of non-morphemic codas using both listener decisions and acoustic analyses. Results showed that utterance po...

Aging in speech production is a multidimensional process. Biological, cognitive, social, and communicative factors can change over time, stay relatively stable, or may even compensate for each other. In this longitudinal work, we focus on stability at the laryngeal supralaryngeal levels discourse particle euh produced by 10 older French-speaking females two times, years apart. Recognizing multi...

The most common approaches to automatic emotion recognition rely on utterance level prosodic features. Recent studies have shown that utterance level statistics of segmental spectral features also contain rich information about expressivity and emotion. In our work we introduce a more fine-grained yet robust set of spectral features: statistics of Mel-Frequency Cepstral Coefficients computed ov...

This paper proposes an improved approach of summarization for spoken multi-party interaction, in which a multi-layer graph with hidden parameters is constructed. The graph includes utterance-to-utterance relation, utterance-to-parameter weight, and speaker-to-parameter weight. Each utterance and each speaker are represented as a node in the utterance-layer and speaker-layer of the graph respect...