Readings in speech recognition

By A. Waibel, Mclloll Univerity. 1990

How researchers see this paper

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

In Speech & Audio

Citations in the corpus

A Convolutional Neural Network for Modelling Sentences (2014, methodology): “In the model, a convolutional layer of the narrow type is applied to the sentence matrix s , where each column corresponds to the feature vector w i ∈ R d of a word in the sentence: To address the problem of varying sentence lengths, the Max-TDNN takes the maximum of each row in the resulting matrix”
Neural network-based face detection (1996, methodology): “Similar input connection patterns are commonly used in speech and character recognition tasks [Waibel et al. , 1989, Le Cun et al. , 1989].”
Markovian Models for Sequential Data (2004, methodology): “An early review of alternative methods based on HMMs or related to HMMs, also for speech recognition, can be found in the collection of papers [25].”
Monte Carlo Hidden Markov Models: Learning Non-Parametric Models of Partially Observable Stochastic Processes (1999, methodology): “Hidden Markov models are often the method of choice in areas such as speech recognition [27] [33], natural language processing [3], robotics [21] [29], biological sequence analysis [11] [16], and time series analysis [10].”
Learning Weakly Supervised Multimodal Phoneme Embeddings (2017, background): “The input to the network during training consists of pairs of stacked features x 1 and x 2 and a label y ∈ { 0 , 1 } , where y = 1 if x 1 and x 2 represent the same word, and y = 0 otherwise. x 1 and x 2 represent stacks of frames that are in correspondence across the two words: for same-word pairs,”
Word Sense Disambiguation: The State of the Art (2005, methodology): “…were rediscovered first in speech processing (e.g. Jelinek, 1976; see the overview by Church and Mercer, 1993, and the collection of reprints by Waibel and Lee, 1990) and were immediately applied to written language analysis (e.g., in the work of Bahl and Mercer , 1976 ; Debili, 1977; etc.)…”
A Gesture Based Interface for Human-Robot Interaction (2000, background): “It has become highly popular in the speech recognition community cf. Waibel and Lee, 1990, since it compensates for variations in the timing of spoken language and gestures.”
Sequence Classification Restricted Boltzmann Machines With Gated Units (2020, methodology): “The sequence classiﬁcation problem has attracted research in dynamic Bayesian models, such as hidden Markov models (HMMs) [11] and conditional random ﬁelds (CRFs) [12].”