Eric Sanders

Annotation in the SpeechDat Projects

A large set of spoken language resources (SLR) for various European languages is being compiled in several SpeechDat projects with the aim to train and test speech recognizers for voice driven services, mainly over telephone lines. This paper is focused on the annotation conventions applied for the Speechdat SLR. These SLR contain typical examples of short monologue speech utterances with simple orthographic transcriptions in a hierarchically simple annotation structure. The annotation conventions and their underlying principles are described and compared to approaches used for related SLR. The synchronization of the orthographic transcriptions with the corresponding speech files is addressed, and the impact of the selected approach for capturing specific phonological and phonetic phenomena is discussed. In the SpeechDat projects a number of tools have been developed to carry out the transcription of the speech. In this paper, a short description of these tools and their properties is provided. For all SpeechDat projects, an internal validity check of the databases and their annotations is carried out. The procedure of this validation campaign, the performed evaluations, and some of the results are presented.

Validation of spoken language resources: an overview of basic aspects

Spoken language resources (SLRs) are essential for both research and application development. In this article we clarify the concept of SLR validation. We define validation and how it differs from evaluation. Further, relevant principles of SLR validation are outlined. We argue that the best way to validate SLRs is to implement validation throughout SLR production and have it carried out by an external and experienced institute. We address which tasks should be carried out by the validation institute, and which not. Further, we list the basic issues that validation criteria for SLR should address. A standard validation protocol is shown, illustrating how validation can prove its value throughout the production phase in terms of pre-validation, full validation and pre-release validation.

Using Demographics in Predicting Election Results with Twitter

The results of two Dutch elections are predicted by counting political party mentions from tweets. In an attempt to improve the predictions, gender and age information from the Twitter users is automatically derived and used to adapt the party counts to the demographics in the election turnout. The prediction improves only slightly in one of the elections where the correlation between election outcome and Twitter-based prediction was relatively lower to begin with (0.86 versus 0.97). The relatively inaccurate estimation of Twitter user age may hinder a larger improvement.

What Weighs for Word Stress? Big Data Mining and Analyses of Phonotactic Distributions in Brazilian Portuguese

For about four decades, phonological theories have claimed that word stress assignment depends on the word’s syllabic phonotactic complexity in relation to syllabic position. This study analyzes the phonotactic implications for word stress Brazilian Portuguese. After creating a phonotactic corpus and applying Random Forest modeling, phonotactic distributions for word stress were found to be bound to stress pattern and word length in number of syllables. To account for these observations, models of word naming must be extended with aspects of word stress.