Grégory Senay

Unsupervised face identification in TV content using audio-visual sources

Our goal is to automatically identify faces in TV content without pre-defined dictionary of identities. Most of methods are based on identity detection (from OCR and ASR) and require a propagation strategy based on visual clusterings. In TV content, people appear with many variation making the clustering very difficult. In this case, identifying speakers can be a reliable link to identify faces. In this work, we propose to combine reliable unsupervised face and speaker identification systems through talking-faces detection in order to improve face identification results. First, OCR and ASR results are combined to extract locally the identities. Then, the reliable visual associations are used to propagate those identities locally. The reliable identified faces are used as unsupervised models to identify similar faces. Finally speaker identities are propagated to the faces in case of lip activity detection. Experiments performed on the REPERE database show an improvement of the recall of +5% compared to the baseline, without degrading the precision.

Person name recognition in ASR outputs using continuous context models

The detection and characterization, in audiovisual documents, of speech utterances where person names are pronounced, is an important cue for spoken content analysis. This paper tackles the problematic of retrieving spoken person names in the 1-Best ASR outputs of broadcast TV shows. Our assumption is that a person name is a latent variable produced by the lexical context it appears in. Thereby, a spoken name could be derived from ASR outputs even if it has not been proposed by the speech recognition system. A new context modelling is proposed in order to capture lexical and structural information surrounding a spoken name. The fundamental hypothesis of this study has been validated on broadcast TV documents available in the context of the REPERE challenge.

A segment-level confidence measure for Spoken Document Retrieval

This paper presents a semantic confidence measure that aims to predict the relevance of automatic transcripts for a task of Spoken Document Retrieval (SDR). The proposed predicting method relies on the combination of Automatic Speech Recognition (ASR) confidence measure and a Semantic Compacity Index (SCI), that estimates the relevance of the words considering the semantic context in which they occurred. Experiments are conducted on the French Broadcast news corpus ESTER, by simulating a classical SDR usage scenario: users submit text-queries to a search engine that is expected to return the most relevant documents regarding the query. Results demonstrate the interest of using semantic level information to predict the transcription indexability.

Towards the Improvement of Topic Priority Assignment Using Various Topic Detection Methods for E-reputation Monitoring on Twitter

Topic priority assignment is defined in RepLab-2013 as labelling a topic according to its level of priority (alert, mildly important or unimportant) in order to highlight topics requiring immediate attention for online reputation monitoring. Although they are strongly linked, topic detection and priority assignment have been previously treated as separate tasks. We study the impact of integrating topic detection outputs in the process of topic priority assignment.