This paper first describes the aims of the prosodic annotation for (part of) the Spoken Dutch Corpus (Corpus Gesproken Nederlands, CGN), and the procedures that are currently being developed to produce the annotation. It further reports on a pilot study that was run to estimate the costs and the attainable quality (in terms of inter-transcriber consistency) of the envisaged annotation. It is ou...

Managing a large-scale speech transcription task with a team of human transcribers requires effective quality control and workload distribution. As it becomes easier and cheaper to collect massive audio corpora the problem is magnified. Relying on expert review or transcribing all speech multiple times is impractical. Furthermore, speech that is difficult to transcribe may be better handled by ...

We present a preliminary analysis of transcriber consistency in labeling and segmentation of words and phones in the Buckeye corpus of spontaneous, informal speech. We find that pairwise inter-transcriber agreement on exact phone label match was 76%, and segmentation agreement within 20% of phone pair length was 75%, though longer phones are more consistently segmented than shorter phones. Patt...

We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion. This is done by specifying a fixed time budget, and then automatically choosing location and size of segments for correction such that the number of corrected errors is maximized. The core components, as suggested by previous research [1], are a utility model that estimates ...

The thesis presents a novel situation awareness tool for sensing classification. We proposed a general scheme for sensing, and applied that to build an acoustic tool for teams of first responders and emergency personnel. It constitutes an audio interface for reliably recording and disseminating situation progress as extracted from the team’s audio communications. The tool that we built is inten...

In this paper, we present the application of a novel automatic prosodic labeling methodology for speeding up the manual labeling of the Glissando corpus (Spanish read news items). The methodology is based on the use of soft classification techniques. The output of the automatic system consists on a set of label candidates per word. The number of predicted candidates depends on the degree of cer...

ne lesson offered by historical studies of musical styles is that the greatest composers almost never abandon their musical heritage entirely even in their most progressive compositions. They tend to build their works upon existing styles and genres, and then transform them into new styles in ways unprecedented in their times. Josquin des Prez, the “Beethoven of the Renaissance,” has been regar...

In this paper a new auditory model-based transcriber of vocal melodic queries is presented. Our experiments show that the new system can transcribe queries with an accuracy between 76 % (whistling) and 85 % (singing with syllables), and that it outperforms four state-of-the-art systems it was compared with.

A set of tools to analyze inconsistencies observed in a Cat_ToBI labeling experiment are presented. We formalize and use the metrics that are commonly used in inconsistency tests. The metrics are systematically applied to analyze the robustness of every symbol and every pair of transcribers. The results reveal agreement rates for this study that are comparable to previous ToBI inter-reliability...