Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features
نویسندگان
چکیده
Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.
منابع مشابه
Building an integrated prosodic model of German
The intellegibility and naturalness of synthetic speech strongly depends on its prosodic quality. Departing from works by Mixdorff on a linguistically motivated model of German intonation based on the Fujisaki model, the current paper presents statistical results concerning the relationship between linguistic and phonetic information underlying an utterance and its prosodic features. Statistica...
متن کاملProsody Prediction from Linguistically Enriched Documents Based on a Machine Learning Approach
One of the main aspects in text-to-speech synthesis is the successful prediction of prosodic events. In this work we deal with the prediction of prosodic phrase breaks, accent tones and boundary tones from a linguistically XML-based enriched input (SOLE-ML) produced by a Natural Language Generator (NLG) system. We first extended the original specification of SOLE-ML in order for the NLG to prod...
متن کاملUnsupervised Extraction of Prosodic Structure
Our approach for unsupervised extraction of prosodic structure in spontaneous speech consists of the four steps: chunking into interpausal units, syllable nucleus extraction, prosodic boundary detection, and pitch accent detection. The extraction is based on acoustic features derived from F0 parameterization, and on energy and segment duration features. Phrase boundaries and accents are detecte...
متن کاملInfluence of syntax on prosodic boundary prediction
We compare the effectiveness of different syntactic features and representations for prosodic boundary prediction, setting out to clarify which representations are most suitable for this task. We took a machine learning approach, and ran a series of eight experiments. The results show that the representations have different strengths and that a combination yields the best result. We also find t...
متن کاملThe psi/phi architecture for prosodic parsing
In this paper an architecture and an implementation for a linguistically based prosodic analyser is presented. The implementation is designed to handle typical prosodic input in the form of parallel input channels, and processes each input channel independently in a data-directed, phonologically motivated configuration of partly parallel, partly cascaded feature modules and module clusters, eac...
متن کامل