Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery

By Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield, S. Lowe. 2014

86 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction, 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 Natural Language Processing

In Information Extraction

In Signal Processing

Citations in the corpus

Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, background): “A different line of work employs probabilistic graphical models to jointly segment and cluster the speech signal (Varadarajan et al., 2008; Zhang & Glass, 2009; Gish et al., 2009; Lee & Glass, 2012; Siu et al., 2014; Lee et al., 2015; Ondel et al., 2016; Kamper et al., 2016; 2017a).”
A segmental framework for fully-unsupervised large-vocabulary speech recognition (2016, methodology): “…(GMMs) to produce frame-level posteriorgrams [9,10], us-ing unsupervised hidden Markov models (HMMs) to obtain discrete categorical output in terms of discovered subword units [2,11,12], and using unsupervised neural networks (NNs) to obtain frame-level continuous vector representations [13–15].”
An empirical evaluation of zero resource acoustic unit discovery (2017, background): “Finally, previous work like [14, 15] presented the success of using unit- or word-level acoustic patterns discovered from fully unsupervised setting to provide competitive performance in spoken document topical classification and clustering, we also explicitly measure our AUD utility of learning doc”
The zero resource speech challenge 2015 (2015, result): “These two levels have already been investigated in previous work (see [1, 2, 3, 4, 5, 6, 7], and [8, 9, 10, 11], respectively), but the performance of the different systems has not yet been compared using common evaluation metrics and data sets.”
Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching (2018, methodology): “Another line of research uses a simpler segmentation method as an initialization, and jointly trains the segmenting and acoustic models for phonemes or words (Kamper et al., 2015; Glass, 2003; Siu et al., 2014; Lee and Glass, 2012).”
Discovering linguistic structures in speech: models and applications (2014, background): “However, it did not receive significant attention again until the mid to late 2000’s, when the authors of [50, 169] began investigating the use of self-”
Unsupervised word discovery from speech using automatic segmentation into syllable-like units (2015, result): “In contrast to earlier work, which has used dynamic time-warping (DTW) [3-6], high-order Markov-approximations [7], HMMs [8], or spectrotemporal parametric models [9] for finding recurring fragments of audio, the present work attempts to bootstrap the learning process with the help via the rhythmic ”
Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017 (2017, methodology): “Transformation estimation is done by running an out-of-thebox acoustic model training pipeline, similar to [18].”
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge (2020, methodology): “Early approaches to acoustic unit discovery typically combined clustering methods with hidden Markov models [15–19].”