This article describes the preparation, recording and orthographic transcription of a new speech corpus, the Nijmegen Corpus of Casual French (NCCFr). The corpus contains a total of over 36 hours of recordings of 46 French speakers engaged in conversations with friends. Casual speech was elicited during three different parts, which together provided around ninety minutes of speech from every pair of speakers. While Parts 1 and 2 did not require participants to perform any specific task, in Part 3 participants negotiated a common answer to general questions about society. Comparisons with the ESTER corpus of journalistic speech show that the two corpora contain speech of considerably different registers. A number of indicators of casualness, including swear words, casual words, verlan, disfluencies and word repetitions, are more frequent in the NCCFr than in the ESTER corpus, while the use of double negation, an indicator of formal speech, is less frequent. In general, these estimates of casualness are constant through the three parts of the recording sessions and across speakers. Based on these facts, we conclude that our corpus is a rich resource of highly casual speech, and that it can be effectively exploited by researchers in language science and technology.

No abstract

This tutorial is based on modification of the professor nomination lecture presented two years ago in front of the Scientific Council of the Czech Technical University in Prague [16].It is devoted to the techniques for the models developing suitable for processes forecasting in complex systems. Because of the high sensitivity of the processes to the initial conditions and, consequently, due to our limited possibilities to forecast the processes for the long-term horizon, the attention is focused on the techniques leading to practical applications of the short term prediction models. The aim of this tutorial paper is to bring attention to possible difficulties which designers of the predicting models and their users meet and which have to be solved during the prediction model developing, validation, testing, and applications. The presented overview is not complete, it only reflects the author's experience with developing of the prediction models for practical tasks solving in banking, meteorology, air pollution and energy sector. The paper is completed by an example of the global solar radiation prediction which forms an important input for the electrical energy production forecast from renewable sources. The global solar radiation forecasting is based on numerical weather prediction models. The time-lagged ensemble technique for uncertainty quantification is demonstrated on a simple example.

The automatic recognition of MP3 compressed speech presents a challenge to the current systems due to the lossy nature of compression which causes irreversible degradation of the speech wave. This article evaluates the performance of a recognition system optimized for MP3 compressed speech with current state-of-the-art acoustic modelling techniques and one specific front-end compensation method. The article concentrates on acoustic model adaptation, discriminative training, and additional dithering as prominent means of compensating for the described distortion in the task of phoneme and large vocabulary continuous speech recognition (LVCSR). The experiments presented on the phoneme task show a dramatic increase of the recognition error for unvoiced speech units as a direct result of compression. The application of acoustic model adaptation has proved to yield the highest relative contribution while the gain of discriminative training diminished with decreasing bit-rate. The application of additional dithering yielded a consistent improvement only for the MFCC features, but the overall results were still worse than those for the PLP features.

No abstract