Forts d’une utilisation couronnée de succès en traduction automatique, les systèmes end-to-end dont la sortie réside en une suite de caractères, ont vu leur utilisation étendue à la transcription automatique de la parole. De nombreuses comparaisons ont alors été effectuées sur des corpus anglais libres de droits, de parole lue. Nous proposons ici de réaliser une comparaison entre deux systèmes état de l’art, non pas sur de la parole lue mais bel et bien sur un corpus d’émissions audiovisuelles françaises présentant différents degrés de spontanéité. Le premier est un end-to-end et le second est un système hybride (HMM/DNN). L’obtention de résultats satisfaisants pour le end-to-end nécessitant un lexique et modèle de langage dédiés, il est intéressant de constater qu’une meilleure intégration dans les systèmes hybrides (HMM/DNN) est source de performances supérieures, notamment en Français où le contexte est primordial pour capturer un énoncé.

Nous nous intéressons à l’évaluation de la qualité des systèmes de reconnaissance de la parole étant donné une tâche de compréhension. L’objectif de ce travail est de fournir un outil permettant la sélection d’un système de reconnaissance automatique de la parole le plus adapté pour un système de dialogue donné. Nous comparons ici différentes métriques, notamment le WER, NE-WER et ATENE métrique proposée récemment pour l’évaluation des systèmes de reconnaissance de la parole étant donné une tâche de reconnaissance d’entités nommées. Cette dernière métrique montrait une meilleure corrélation avec les résultats de la tâche globale que toutes les autres métriques testées. Nos mesures indiquent une très forte corrélation avec la mesure ATENE et une moins forte avec le WER.

L’étude porte sur l’apport d’un réseau de neurones récurrent (Recurrent Neural Network RNN) bidirectionnel encodeur/décodeur avec mécanisme d’attention pour une tâche de compréhension de la parole. Les premières expériences faites sur le corpus ATIS confirment la qualité du système RNN état de l’art utilisé pour cet article, en comparant les résultats obtenus à ceux récemment publiés dans la littérature. Des expériences supplémentaires montrent que les RNNs avec mécanisme d’attention obtiennent de meilleures performances que les RNNs récemment proposés pour la tâche d’étiquetage en concepts sémantiques. Sur le corpus MEDIA, un corpus français état de l’art pour la compréhension dédié à la réservation d’hôtel et aux informations touristiques, les expériences montrent qu’un RNN bidirectionnel atteint une f-mesure de 79,51 tandis que le même système intégrant le mécanisme d’attention permet d’atteindre une f-mesure de 80,27.

In this article, we present the RATP-DECODA Corpus which is composed by a set of 67 hours of speech from telephone conversations of a Customer Care Service (CCS). This corpus is already available on line at http://sldr.org/sldr000847/fr in its first version. However, many enhancements have been made in order to allow the development of automatic techniques to transcript conversations and to capture their meaning. These enhancements fall into two categories: firstly, we have increased the size of the corpus with manual transcriptions from a new operational day; secondly we have added new linguistic annotations to the whole corpus (either manually or through an automatic processing) in order to perform various linguistic tasks from syntactic and semantic parsing to dialog act tagging and dialog summarization.

This paper describes the Spoken Language Translation system developed by the LIUM for the IWSLT 2014 evaluation campaign. We participated in two of the proposed tasks: (i) the Automatic Speech Recognition task (ASR) in two languages, Italian with the Vecsys company, and English alone, (ii) the English to French Spoken Language Translation task (SLT). We present the approaches and specificities found in our systems, as well as the results from the evaluation campaign.

In this paper, we present improvements made to the TED-LIUM corpus we released in 2012. These enhancements fall into two categories. First, we describe how we filtered publicly available monolingual data and used it to estimate well-suited language models (LMs), using open-source tools. Then, we describe the process of selection we applied to new acoustic data from TED talks, providing additions to our previously released corpus. Finally, we report some experiments we made around these improvements.

This paper presents the corpus developed by the LIUM for Automatic Speech Recognition (ASR), based on the TED Talks. This corpus was built during the IWSLT 2011 Evaluation Campaign, and is composed of 118 hours of speech with its accompanying automatically aligned transcripts. We describe the content of the corpus, how the data was collected and processed, how it will be publicly available and how we built an ASR system using this data leading to a WER score of 17.4 %. The official results we obtained at the IWSLT 2011 evaluation campaign are also discussed.

This paper describes the three systems developed by the LIUM for the IWSLT 2011 evaluation campaign. We participated in three of the proposed tasks, namely the Automatic Speech Recognition task (ASR), the ASR system combination task (ASR_SC) and the Spoken Language Translation task (SLT), since these tasks are all related to speech translation. We present the approaches and specificities we developed on each task.

This paper describes the two systems developed by the LIUM laboratory for the 2010 IWSLT evaluation campaign. We participated to the new English to French TALK task. We developed two systems, one for each evaluation condition, both being statistical phrase-based systems using the the Moses toolkit. Several approaches were investigated.

Large vocabulary automatic speech recognition (ASR) technologies perform well in known, controlled contexts. However recognition of proper nouns is commonly considered as a difficult task. Accurate phonetic transcription of a proper noun is difficult to obtain, although it can be one of the most important resources for a recognition system. In this article, we propose methods of automatic phonetic transcription applied to proper nouns. The methods are based on combinations of the rule-based phonetic transcription generator LIA_PHON and an acoustic-phonetic decoding system. On the ESTER corpus, we observed that the combined systems obtain better results than our reference system (LIA_PHON). The WER (Word Error Rate) decreased on segments of speech containing proper nouns, without affecting negatively the results on the rest of the corpus. On the same corpus, the Proper Noun Error Rate (PNER, which is a WER computed on proper nouns only), decreased with our new system.

This work adresses the use of confidence measures for extracting well recognized words with very low error rate from automatically transcribed segments in a unsupervised way. We present and compare several confidence measures and propose a method to merge them into a new one. We study its capabilities on extracting correct recognized word-segments compared to the amount of rejected words. We apply this fusion measure to select audio segments composed of words with a high confidence score. These segments come from an automatic transcription of french broadcast news given by our speech recognition system based on the CMU Sphinx3.3 decoder. Injecting new data resulting from unsupervised treatments of raw audio recordings in the training corpus of acoustic models gives statistically significant improvement (95% confident interval) in terms of word error rate. Experiments have been carried out on the corpus used during ESTER, the french evaluation campaign.