Speech recognition technology suffers from a lack of robustness which limits its usability for fully automated speech-to-text transcription, and manual correction is generally required to obtain perfect transcripts. In this paper, we propose a general scheme for semi-automatic transcription, in which the system and the transcriptionist contribute jointly to the speech transcription. The proposed system relies on the editing of confusion networks and on reactive decoding, the latter one being supposed to take benefits from the manual correction and improve the error rates. In order to reduce the correction time, we evaluate various strategies aiming to guide the transcriptionist towards the critical areas of transcripts. These strategies are based on graph density-based criterion and two semantic consistency criterion; using a corpus-based method and a web-search engine. They allow to indicate to the user the areas which present severe lacks of understandability. We evaluate these driving strategies by simulating the correction process of French broadcast news transcriptions. Results show that interactive decoding improves the correction act efficiency with all driving strategies and semantic information must be integrated into the interactive decoding process.

Dans cet article nous proposons une nouvelle méthode pour l’identification du genre vidéo qui repose sur une analyse de leur contenu linguistique. Cette approche consiste en l’analyse des mots apparaissant dans les transcriptions des pistes audio des vidéos, obtenues à l’aide d’un système de reconnaissance automatique de la parole. Les expériences sont réalisées sur un corpus composé de dessins animés, de films, de journaux télévisés, de publicités, de documentaires, d’émissions de sport et de clips de musique. L’approche proposée permet d’obtenir un taux de bonne classification de 74% sur cette tâche. En combinant cette approche avec des méthodes reposant sur des paramètres acoustiques bas-niveau, nous obtenons un taux de bonne classification de 95%.

Most of the Web-based methods for lexicon augmenting consist in capturing global semantic features of the targeted domain in order to collect relevant documents from the Web. We suggest that the local context of the out-of-vocabulary (OOV) words contains relevant information on the OOV words. With this information, we propose to use the Web to build locally-augmented lexicons which are used in a final local decoding pass. First, an automatic web based OOV word detection method is proposed. Then, we demonstrate the relevance of the Web for the OOV word retrieval. Different methods are proposed to retrieve the hypothesis words. We finally retrieve about 26% of the OOV words with a lexicon increase of less than 1000 words using the reference context.