Search

HighlightsReview of the impact of dialogue representations and classification methods.We discuss the impact of discriminative words in terms of transcription accuracy.Original study evaluating the impact of the WER in the LDA topic space. A review is proposed of the impact of word representations and classification methods in the task of theme identification of telephone conversation services having highly imperfect automatic transcriptions. We firstly compare two word-based representations using the classical Term Frequency-Inverse Document Frequency with Gini purity criteria (TF-IDF-Gini) method and the latent Dirichlet allocation (LDA) approach. We then introduce a classification method that takes advantage of the LDA topic space representation, highlighted as the best word representation. To do so, two assumptions about topic representation led us to choose a Gaussian Process (GP) based method. Its performance is compared with a classical Support Vector Machine (SVM) classification method. Experiments showed that the GP approach is a better solution to deal with the multiple theme complexity of a dialogue, no matter the conditions studied (manual or automatic transcriptions) (Morchid et al., 2014). In order to better understand results obtained using different word representation methods and classification approaches, we then discuss the impact of discriminative and non-discriminative words extracted by both word representations methods in terms of transcription accuracy (Morchid et al., 2014). Finally, we propose a novel study that evaluates the impact of the Word Error Rate (WER) in the LDA topic space learning process as well as during the theme identification task. This original qualitative study points out that selecting a small subset of words having the lowest WER (instead of using all the words) allows the system to better classify automatic transcriptions with an absolute gain of 0.9 point, in comparison to the best performance achieved on this dialogue classification task (precision of 83.3%).

This paper describes a new kind of language models based on the possibility theory. The purpose of these new models is to better use the data available on the Web for language modeling. These models aim to integrate information relative to impossible word sequences. We address the two main problems of using this kind of model: how to estimate the measures for word sequences and how to integrate this kind of model into the ASR system. We propose a word-sequence possibilistic measure and a practical estimation method based on word-sequence statistics, which is particularly suited for estimating from Web data. We develop several strategies and formulations for using these models in a classical automatic speech recognition engine, which relies on a probabilistic modeling of the speech recognition process. This work is evaluated on two typical usage scenarios: broadcast news transcription with very large training sets and transcription of medical videos, in a specialized domain, with only very limited training data. The results show that the possibilistic models provide significantly lower word error rate on the specialized domain task, where classical n-gram models fail due to the lack of training materials. For the broadcast news, the probabilistic models remain better than the possibilistic ones. However, a log-linear combination of the two kinds of models outperforms all the models used individually, which indicates that possibilistic models bring information that is not modeled by probabilistic ones.

(Impact-F 1.46 estim. in 2012); International audience; The training of state-of-the-art automatic speech recognition (ASR) systems requires huge relevant training corpora. The cost of such databases is high and remains a major limitation for the development of speech-enabled applications in particular contexts (e.g. low-density languages, or specialized domains). On the other hand, a large amount of data can be found in news prompts, movie subtitles or scripts, etc. The use of such data as training corpus could provide a low-cost solution to the acoustic model estimation problem. Unfortunately, prior transcripts are seldom exact with respect to the content of the speech signal, and suffer from a lack of temporal information. This paper tackles the issue of prompt-based speech corpora improvement, by addressing the problems mentioned above. We propose a method allowing to locate accurate transcript segments in speech signals and automatically correct errors or lack of transcript surrounding these segments. This method relies on a new decoding strategy where the search algorithm is driven by the imperfect transcription of the input utterances. The experiments are conducted on the French language, by using the ESTER database and a set of records (and associated prompts) from RTBF (Radio Télévision Belge Francophone). The results demonstrate the effectiveness of the proposed approach, in terms of both error correction and text-to-speech alignment.

Audio pattern classification represents a particular statistical classification task and includes, for example, speaker recognition, language recognition, emotion recognition, speech recognition and, recently, video genre classification. The feature being used in all these tasks is generally based on a short-term cepstral representation. The cepstral vectors contain at the same time useful information and nuisance variability, which are difficult to separate in this domain. Recently, in the context of GMM-based recognizers, a novel approach using a Factor Analysis (FA) paradigm has been proposed for decomposing the target model into a useful information component and a session variability component. This approach is called Joint Factor Analysis (JFA), since it models jointly the nuisance variability and the useful information, using the FA statistical method. The JFA approach has even been combined with Support Vector Machines, known for their discriminative power. In this article, we successfully apply this paradigm to three automatic audio processing applications: speaker verification, language recognition and video genre classification. This is done by applying the same process and using the same free software toolkit. We will show that this approach allows for a relative error reduction of over 50% in all the aforementioned audio processing tasks.