Discussion

Neubig, Thomas S.

doi:10.7551/mitpress/9780262042475.003.0010

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further set the results into perspective we compared the proposed algorithm with the algorithm proposed in [11] using the freely available software published with the paper [14]. Table 1 summarizes the different setups.…”

Section: Resultsmentioning

confidence: 99%

Iterative Bayesian word segmentation for unsupervised vocabulary discovery from phoneme lattices

Heymann

Walter

Haeb‐Umbach

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper we present an algorithm for the unsupervised segmentation of a lattice produced by a phoneme recognizer into words. Using a lattice rather than a single phoneme string accounts for the uncertainty of the recognizer about the true label sequence. An example application is the discovery of lexical units from the output of an error-prone phoneme recognizer in a zero-resource setting, where neither the lexicon nor the language model (LM) is known. We propose a computationally efficient iterative approach, which alternates between the following two steps: First, the most probable string is extracted from the lattice using a phoneme LM learned on the segmentation result of the previous iteration. Second, word segmentation is performed on the extracted string using a word and phoneme LM which is learned alongside the new segmentation. We present results on lattices produced by a phoneme recognizer on the WSJ-CAM0 dataset. We show that our approach delivers superior segmentation performance than an earlier approach found in the literature, in particular for higher-order language models.

show abstract

Section: Resultsmentioning

confidence: 99%