The performance of Automatic Speech Recognition (ASR) systems drops dramatically when used in noisy environments. Speech analytics suffer from this poor quality of automatic transcriptions. In this paper, we seek to identify themes from dialogues of telephone conversation services using multiple topic-spaces estimated with a Latent Dirichlet Allocation (LDA) approach. This technique consists in estimating several topic models that offer different views of the document. Unfortunately, such a multi-model approach also introduces additional variabilities due to the model diversity. We propose to extract the useful information from the full model-set by using an i-vector based approach, previously developed in the context of speaker recognition. Experiments are conducted on the DECODA corpus, that contains records from the call center of the Paris Transportation Company. Results show the effectiveness of the proposed representation paradigm, our identification system reaching an accuracy of 84.7%, with a gain of 3.3 points compared to the baseline.
Bibliographic reference. Morchid, Mohamed / Bouallegue, Mohamed / Dufour, Richard / Linarès, Georges / Matrouf, Driss / Mori, Renato De (2014): "I-vector based representation of highly imperfect automatic transcriptions", In INTERSPEECH-2014, 1870-1874.