Towards unsupervised pattern discovery in speech

By Alex Seungryong Park, James R. Glass. 2005

86 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Speech & Audio

In Signal Processing

Citations in the corpus

Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, methodology): “One family of techniques is based upon Segmental Dynamic Time Warping (S-DTW) (Park & Glass, 2005; 2008; Jansen et al., 2010; Jansen & Van Durme, 2011), which uses a self-comparison algorithm to identify relatively long duration (on the order of a second) patterns which frequently reoccur in a speec”
Multilingual bottle-neck feature learning from untranscribed speech (2017, unknown): “Recently there is an increasing research interest in unsupervised speech processing, which usually involves unsupervised discovery of linguistic units [1, 2, 3], and the derived techniques have been used in different applications, such as retrieval of spoken queries in a speech database [4, 5, 6] an”
Towards spoken term discovery at scale with zero resources (2010, methodology): “While it is desirable to have this extra capacity, it comes at significant computational cost.”
Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery (2014, background): “A similar approach has also been proposed in Park and Glass (2005) and Zhang and Glass (2010) that searches for “similar” regions of speech from in-topic audio recordings.”
Unsupervised Pattern Discovery in Speech (2008, background): “This section motivates and describes a dynamic programming algorithm which we call segmental DTW [23], [24].”
Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions (2012, methodology): “The ecological plausibility of the DTW-based approaches (P&G algorithm [93,94] and the work of McInnes and Goldwater [95]) is greatly enhanced by the work of Unal & Tepedelenlioglu [9] who showed that the DTW computations can be accomplished with artificial neural networks.”