Our results on the OGI spoken name corpus indicate that using syllables in place of phoneme models can help boost system accuracy significantly while helping to reduce the system complexity.
Most European languages are now documented in spoken discourse corpora of variable size, but only English currently disposes of several mid-size and large resources.
Subsequently, it was shown that a linear combination of the two measures yielded a correlation of r = 0.91 and a mean deviation of 10% which is accurate enough to successfully extract PLSR from large spoken language corpora.
Roughly speaking, the corpus consists of those statements that could, for the time being, legitimately be made without reservation in a (sufficiently detailed) textbook.
However, because these classifications seemed somewhat doubtful (and perhaps more representative of American than British English), the verbs were reclassified as according to whether the un- form appears in the British National Corpus (BNC), a 100 million word corpus of spoken and written British English.
The project English as an academic lingua franca (ELFA) based at the University of Helsinki investigates academic discourses, branching out into two parts: one is the ELFA (English as a Lingua Franca in Academic Settings) corpus project, whose major achievement is the 1-million-word ELFA corpus of spoken academic discourse.
Perceptual and acoustic research on dialect variation in the United States requires an appropriate corpus of spoken language materials.
The research group which created the site also has its own site, Survey of English, offering a corpus of spoken and written English.
Corpora of spoken discourse are structured collections of naturally occurring speech (in narrative or conversational form) organized in larger textual units and compiled systematically with a linguistic aim in mind.
We track eye-movements during spoken language comprehension, analyze corpora, study parent-child interactions, conduct training studies to explore the process learning words and grammars, and probe the linguistic intuitions of naïve speakers.
