Le batelier : nocturne à deux voix égales /

For 2 voices and piano.

Les Psaumes de David tout en musique, suivis des Cantiques sacrés : La musique en est rhythmée et disposée à trois parties (voix égales et inégales)

Propriété des éditeurs Marc-Aurel frères

Dispositions légales et réglementaires qui régissent la pêche fluviale en Belgique. Vade-mecum des pêcheurs, gardes-pêche, propriétaires, locataires, etc.

"Publié sous les auspices du Ministère de l'agriculture, Administration des eaux et forêts."

Disposition légales & réglementaires concernant les denrées alimentaires.

Mode of access: Internet.

Recueil des dispositions légales et réglementaires concernant l'exercise de la professsion de sage-femme.

Mode of access: Internet.

El Libro del Governador o Suma de collaciones o de ayuntamientos: versión castellana del "Communiloquium" de Juan de Gales

The intellectual production of Johannes Gallensis (also known as John of Wales, c. 1210/30 – 1285), regent-master of the Friars Minor at Oxford and later a lecturer and Doctor of Theology at Paris, was oriented towards furnishing Catholic preachers with a variety of compilations of moral philosophy aimed to serve them in their pastoral ministry. One of these compilations is the Communiloquium, a manual of a kind, which displays its author's attempt to provide adequate and specific argumentation for admonishing all sorts and types of devotees. Its most prominent characteristic is a highly accurate use of classical auctoritates and exempla, which turned this work into a kind of anthology of quotations and references, for it offered its readers the possibility of citing sources and texts that they themselves had never actually consulted. The impressive number of manuscript copies of the Communiloquium that reached our times bears witness to its great popularity (some one hundred and sixty dispersed in different European libraries, according to Jenny Swanson’s John of Wales. A Study of the Work and Ideas of a Thirteenth-Century Friar). The Communiloquium must have reached the Iberian soil by means of Franciscan friars and soon spread through courtly circles, as much as in the religious milieu, due to the political taint of its first part, rooted in the organological metaphor and containing extensive reflections on the virtues and the due behaviour of a monarch. In the Crown of Aragon, the Communiloquium used to be read out loud even among the artisans. In Castile, on the other hand, particularly between the XIIIth and the XVth centuries, its main audience happened to be the lettered nobility and those intellectuals who, dedicated to composing glosas and specula principum, required its resources...

Development of the 2003 CU-HTK conversational telephone speech transcription system

This paper describes the development of the 2003 CU-HTK large vocabulary speech recognition system for Conversational Telephone Speech (CTS). The system was designed based on a multi-pass, multi-branch structure where the output of all branches is combined using system combination. A number of advanced modelling techniques such as Speaker Adaptive Training, Heteroscedastic Linear Discriminant Analysis, Minimum Phone Error estimation and specially constructed Single Pronunciation dictionaries were employed. The effectiveness of each of these techniques and their potential contribution to the result of system combination was evaluated in the framework of a state-of-the-art LVCSR system with sophisticated adaptation. The final 2003 CU-HTK CTS system constructed from some of these models is described and its performance on the DARPA/NIST 2003 Rich Transcription (RT-03) evaluation test set is discussed.

Unsupervised training for mandarin broadcast news and conversation transcription

A significant cost in obtaining acoustic training data is the generation of accurate transcriptions. For some sources close-caption data is available. This allows the use of lightly-supervised training techniques. However, for some sources and languages close-caption is not available. In these cases unsupervised training techniques must be used. This paper examines the use of unsupervised techniques for discriminative training. In unsupervised training automatic transcriptions from a recognition system are used for training. As these transcriptions may be errorful data selection may be useful. Two forms of selection are described, one to remove non-target language shows, the other to remove segments with low confidence. Experiments were carried out on a Mandarin transcriptions task. Two types of test data were considered, Broadcast News (BN) and Broadcast Conversations (BC). Results show that the gains from unsupervised discriminative training are highly dependent on the accuracy of the automatic transcriptions. © 2007 IEEE.

Discriminative language model adaptation for Mandarin broadcast speech transcription and translation

This paper investigates unsupervised test-time adaptation of language models (LM) using discriminative methods for a Mandarin broadcast speech transcription and translation task. A standard approach to adapt interpolated language models to is to optimize the component weights by minimizing the perplexity on supervision data. This is a widely made approximation for language modeling in automatic speech recognition (ASR) systems. For speech translation tasks, it is unclear whether a strong correlation still exists between perplexity and various forms of error cost functions in recognition and translation stages. The proposed minimum Bayes risk (MBR) based approach provides a flexible framework for unsupervised LM adaptation. It generalizes to a variety of forms of recognition and translation error metrics. LM adaptation is performed at the audio document level using either the character error rate (CER), or translation edit rate (TER) as the cost function. An efficient parameter estimation scheme using the extended Baum-Welch (EBW) algorithm is proposed. Experimental results on a state-of-the-art speech recognition and translation system are presented. The MBR adapted language models gave the best recognition and translation performance and reduced the TER score by up to 0.54% absolute. © 2007 IEEE.

Exploiting Chinese character models to improve speech recognition performance

The Chinese language is based on characters which are syllabic in nature. Since languages have syllabotactic rules which govern the construction of syllables and their allowed sequences, Chinese character sequence models can be used as a first level approximation of allowed syllable sequences. N-gram character sequence models were trained on 4.3 billion characters. Characters are used as a first level recognition unit with multiple pronunciations per character. For comparison the CU-HTK Mandarin word based system was used to recognize words which were then converted to character sequences. The character only system error rates for one best recognition were slightly worse than word based character recognition. However combining the two systems using log-linear combination gives better results than either system separately. An equally weighted combination gave consistent CER gains of 0.1-0.2% absolute over the word based standard system. Copyright © 2009 ISCA.

Language model combination and adaptation using weighted finite state transducers

In speech recognition systems language model (LMs) are often constructed by training and combining multiple n-gram models. They can be either used to represent different genres or tasks found in diverse text sources, or capture stochastic properties of different linguistic symbol sequences, for example, syllables and words. Unsupervised LM adaptation may also be used to further improve robustness to varying styles or tasks. When using these techniques, extensive software changes are often required. In this paper an alternative and more general approach based on weighted finite state transducers (WFSTs) is investigated for LM combination and adaptation. As it is entirely based on well-defined WFST operations, minimum change to decoding tools is needed. A wide range of LM combination configurations can be flexibly supported. An efficient on-the-fly WFST decoding algorithm is also proposed. Significant error rate gains of 7.3% relative were obtained on a state-of-the-art broadcast audio recognition task using a history dependently adapted multi-level LM modelling both syllable and word sequences. ©2010 IEEE.

Improving speech transcription for Mandarin-english translation

This paper describes the development of the CU-HTK Mandarin Speech-To-Text (STT) system and assesses its performance as part of a transcription-translation pipeline which converts broadcast Mandarin audio into English text. Recent improvements to the STT system are described and these give Character Error Rate (CER) gains of 14.3% absolute for a Broadcast Conversation (BC) task and 5.1% absolute for a Broadcast News (BN) task. The output of these STT systems is then post-processed, so that it consists of sentence-like segments, and translated into English text using a Statistical Machine Translation (SMT) system. The performance of the transcription-translation pipeline is evaluated using the Translation Edit Rate (TER) and BLEU metrics. It is shown that improving both the STT system and the post-STT segmentations can lower the TER scores by up to 5.3% absolute and increase the BLEU scores by up to 2.7% absolute. © 2007 IEEE.