Hidden Markov Models for Speech Recognition

By Biing-Hwang Fred Juang, Lawrence R. Rabiner. 1991

Subfields: Natural Language Processing, Speech & Audio

How researchers see this paper

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

In Natural Language Processing

In Speech & Audio

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, background): “We therefore expect that continuing our long-standing effort to understand how humans abilities can emerge without assuming special start up software will be most helpful in explicating the nature of human cognition.”
Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers (2013, methodology): “The predominant technology used to perform this task is the HMM [37], many tools are nowadays available ([5, 41]).”
Subspace distribution clustering hidden Markov model (2001, background): “ture [32], [33], we will not repeat it here.”
Finding a roadmap to achieve large neuromorphic hardware systems (2013, methodology): “…algorithms currently proposed are • Winner-Take-All (WTA) Networks (Lazzaro et al., 1988; Indiveri et al., 2001; Chicca, 2006) • Wordspotting (e.g., Juang and Rabiner, 1991; Lippmann and Jankowski, 1994) in groups of cortical cells In the following paragraphs, we will model the computational load…”
Exact Computation of the Observed Information Matrix for Hidden Markov Models (2002, background): “Standard references for the theory of hidden Markov models are the paper by Juang and Rabiner (1991) and the book by MacDonaldand Zucchini (1997).”
Collapsed Variational Bayesian Inference for Hidden Markov Models (2013, methodology): “Surprisingly, the most efficient method is not the EM algorithm as it has to be implemented in log space (or rescaled) to avoid underflow (Juang and Rabiner, 1991).”
A Hidden Markov Model to detect coded information islands in free text (2013, background): “Hidden Markov models are especially known for their application in temporal pattern recognition such as speech, handwriting, and gesture recognition [18], [19], part-of-speech tagging [20], musical score following [21], and bioinformatics analyses, such as CpG island detection and splice site recogn”
Multi-State Models for Panel Data: The msm Package for R (2011, methodology): “This class of model is commonly used in areas such as speech and signal processing (Juang and Rabiner 1991) and the analysis of biological sequence data (Durbin et al.”
On supervised learning from sequential data with applications for speech regognition (1999, background): “The realignment for each hypothesis to extend is in detail done as follows: Takethe last M words and nd the correct (cross-word) HMMs for each phone at the wordboundaries which don't already cover the maximum available context given the acousticmodel set.”
Multimodal Machine Learning: A Survey and Taxonomy (2017, background): “Given the prominence of hidden Markov models (HMMs) in the speech community at the time [95], it is”
A generalized ARFIMA process with Markov-switching fractional differencing parameter (2009, unknown): “Given that the hidden Markov model has become extremely popular in speech recognition as shown in Juang and Rabiner [24] and Qian and Titterington [25], and in econometrics, finance, genetics, and neurophysiology as outlined in Robert et al.”
Hidden Markov processes (2002, methodology): “To motivate these approaches it is useful to review the role of HMPs in automatic speech recognition applications [173], [263], [165].”
Exploiting Tractable Substructures in Intractable Networks (1995, methodology): “We apply these ideas to hidden Markov modeling (Rabiner & Juang, 1991).”