Gooskens (2003) described an experiment which determined linguistic distances between 15 Norwegian dialects as perceived by Norwegian listeners. The results are compared to Levenshtein distances, calculated on the basis of transcriptions (of the words) of the same recordings as used in the perception experiment. The Levenshtein distance is equal to the sum of the weights of the insertions, dele...

Two transcribers have labeled prosodic events independently on a subset of Switchboard corpus using adapted ToBI (TOnes and Break Indices) system. Transcriptions of two types of pitch accents (H* and L*), phrasal accents (Hand L-) and boundary tones (H% and L%) encoded independently by two transcribers are compared for intertranscriber reliability. Two commonly used methods of reliability measu...

In this paper, we describe and analyse the performance of a simple approach to the alignment of very long speech signals to acoustically inaccurate transcriptions, even when two different languages are employed. The alignment algorithm operates on two phonetic sequences, the first one automatically extracted from the speech signal by means of a phone decoder, and the second one obtained from th...

This study investigates the use of Amazon Mechanical Turk for the transcription of nonnative speech. Multiple transcriptions were obtained from several distinct MTurk workers and were combined to produce merged transcriptions that had higher levels of agreement with a gold standard transcription than the individual transcriptions. Three different methods for merging transcriptions were compared...

Current automatic speech transcription systems can achieve a high accuracy although they still make mistakes. In some scenarios, high quality transcriptions are needed and, therefore, fully automatic systems are not suitable for them. These high accuracy tasks require a human transcriber. However, we consider that automatic techniques could improve the transcriber’s efficiency. With this idea w...

We have been actively collecting data within the JUPITER domain since the beginning of 1997. As was done in previous domains, we first developed a prototype JUPITER system and used it to collect spontaneous speech using a Wizard paradigm, with a human typist in the loop and subjects brought into the lab and given scenarios to solve. At the same time, we solicited read speech using both our Web-...

An interactive speech transcription tool is described. Segmental and tonal transcription may be performed, and the transcriber may get instant feedback on the accuracy and adequacy of the transcription by synthesizing a speech waveform on the fly with the segmental and tonal transcriptions as input. This speech sound may then be examined auditorily. Transcription labels may be moved by simple d...

In this paper, a new system for the automatic transcription of singing sequences into a sequence of pitch and duration pairs is presented. Although such a system may have a wider range of applications, it was mainly developed to become the acoustic module of a queryby-humming (QBH) system for retrieving pieces of music from a digitized musical library. The first part of the paper is devoted to ...

One of the main motivations for publishing this paper is to make available a matrix of phone-distance measures which may be useful in dealing with large corpora of conversational speech. The paper reports how this matrix of phone-distances was created from transcriber labeling disagreements, and how it can be used in a dynamic time warping algorithm to align phonetic transcriptions of conversat...

Users of OCR systems, from different institutions and scientific disciplines, prefer produce transcription styles. This presents a problem for training consistent text recognition neural networks on real-world data. We propose to extend existing with Transcription Style Block (TSB) which can learn data switch between multiple styles without any explicit knowledge rules. TSB is an adaptive insta...