Verbal irony is characterized by the use of specific acoustic modulations, especially global prosodic cues as well as vowel hyperarticulation. Little is known concerning the expression of sarcastic speech in French. Here we report on global prosodic features of sarcastic speech in a corpus of declarative French utterances. Our data show that sarcastic productions are characterized by utterance lengthening, by increased f 0 modulations and a global raising of the pitch level and range. The results are discussed in the light of results on the acoustic features of ironic speech in languages other than French.

No abstract

Information retrieval from speech is a key technology for many applications, as it allows access to large amounts of audio data. This technology requires two major components: an automatic speech recognizer (ASR) and a text-based information retrieval module such as a key word extractor or a named entity recognizer (NER). When combining the two components, the resulting final application needs to be globally optimized. However, ASR and information retrieval are usually developed and optimized separately. The ASR tends to be optimized to reduce the word error rate (WER), a metric which does not take into account the contextual and syntactic roles of the words, which are valuable information for information retrieval systems. In this paper we investigate different ways to tune the ASR for a speech-based NER system. In an end-to-end configuration we also tested several ASR metrics, including WER, NEWER and ATENE, as well as the use of an oracle during the development step. Our results show that using a NER oracle to tune the system reduces the named entity recognition error rate by more than 1% absolute, and using the ATENE metric allows us to reduce it by more than 0.75%. We also show that these optimization approaches favor a higher ASR language model weight which entails an overall gain in NER performance, despite a local increase of the WER.