Jun 16, 2009 · Abstract: This paper investigates a data-driven word decompounding algorithm for use in automatic speech recognition.

This paper investigates a data-driven word decompounding algorithm for use in automatic speech recognition. An existing algorithm, called ldquoMorfessor ...

Abstract—This paper investigates a data-driven word decom- pounding algorithm for use in automatic speech recognition. An.

Bibliographic details on Automatic Word Decompounding for ASR in a Morphologically Rich Language: Application to Amharic.

Media type: E-Article; Title: Automatic Word Decompounding for ASR in a Morphologically Rich Language: Application to Amharic; Contributor: Pellegrini, ...

An automatic speech recognition experiment conducted to see the effect of OOV words on the performance speech recognition system for Amharic (a ...

This paper presents the application of morpheme-based and factored language models in an Amharic speech recognition task. Since using morphemes in both acoustic ...

Automatic word decompounding for ASR in a morphologically rich language: application to Amharic Thomas Pellegrini, Lori Lamel IEEE Transactions on Audio ...

This paper has developed syllableand triphone-based ASR for Amharic and achieved 90.43% and 91.31% word recognition accuracy, respectively, ...

application of automatic word decompounding (using. Harris algorithm) for automatic speech recognition of less-represented languages, specifically Amharic.