Morphological Segmentation for Keyword Spotting

Abstract

We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof-the-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.

Morphological Analysis of the Dravidian Language Family

“…For example, the English word joblessness can be segmented as job+less+ness. When processing morphologically-rich languages, this helps reduce the sparsity created by the higher OOV rate due to productive morphology, and, empirically, has shown to be beneficial in a diverse variety of down-stream tasks, e.g., machine translation (Clifton and Sarkar, 2011), speech recognition (Afify et al, 2006), keyword spotting (Narasimhan et al, 2014) and parsing (Seeker and Özlem Çetinoğlu, 2015 and unsupervised approaches have been successful, but, when annotated data is available, supervised approaches typically greatly outperform unsupervised approaches (Ruokolainen et al, 2013).…”

Combination of search techniques for improved spotting of OOV keywords

“…For detecting OOV keywords, one must either resort to (i) hybrid fuzzy phonetic search strategies, in which recognition is done in terms of words, but the search is done fuzzily based on phonetic strings, allowing for inexact matches [1,8,9,2], or, (ii) recognition in terms of shorter units [10,3,11,12,13,5,14] that have a higher chance of allowing a new word. In this paper, we focus mainly on the first category.…”

“…When dealing with OOV keywords, things become more complicated; as demonstrated in the literature, [3,5], state-We thank all members of the BBN Speech and Language group for useful discussions, especially those on the Babel project. We also acknowledge the contribution of the BUT partners of the BABELON team who provided MLP acoustic features.…”

A Joint Model of Orthography and Morphological Segmentation

“…Morphological segmentation is useful for NLP applications, such as, automatic speech recognition (Afify et al, 2006), keyword spotting (Narasimhan et al, 2014), machine translation (Clifton and Sarkar, 2011) and parsing (Seeker and Ç etinoglu, 2015). Prior work cast the problem as surface segmentation: a word form w is segmented into a sequence of substrings whose concatenation is w. In this paper, we introduce the problem of canonical segmentation: w is analyzed as a sequence of canonical morphemes, based on a set of word forms that have been "canonically" annotated for supervised learning.…”