Rephrasing-based speech intelligibility enhancement
2013 (English)In: Proceedings of 2013 INTERSPEECH, 2013, 3587-3591 p.Conference paper (Refereed)
Existing algorithms for improving speech intelligibility in a noisy environment generally focus on modifying the acoustic features of live, recorded or synthesized speech while preserving the phonetic composition (the message). In this paper, we present an algorithm for text-to-speech systems that operates at a higher level of abstraction, the message-level. We use a paraphrasing system to adjust the linguistic content of the intended message such that the speech intelligibility improves under noisy conditions. To distinguish the intelligibility among paraphrases, we use the numerical integration of a normalized log-likelihood function over different signal-to-noise conditions. Objective evaluation results show that the developed measure is able to distinguish the intelligibility among paraphrases. Results from subjective evaluation confirm the effectiveness of our objective measure.
Place, publisher, year, edition, pages
2013. 3587-3591 p.
, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISSN 2308-457X
Message-level objective measure, Speech intelligibility
Other Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-150995ScopusID: 2-s2.0-84906257395OAI: oai:DiVA.org:kth-150995DiVA: diva2:746305
14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013, 25 August 2013 through 29 August 2013, Lyon, France
QC 201409122014-09-122014-09-122014-09-12Bibliographically approved