Stochastic modeling for automatic speech understanding

How researchers see this paper

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

Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation (2024, background): “The mathematical formulations date back to 20 and original use cases focused on compressing communication 21 andspeechrecognition 22 – 24 .”
Markovian Models for Sequential Data (2004, methodology): “The application of HMMs to speech was independently proposed by [21] and [22], and popularized by [23], [24], and [17].”
A Statistical Approach to Machine Translation (1990, methodology): “Statistical methods have proven their value in automatic speech recognition (Bahl et al. 1983) and have recently been applied to lexicography (Sinclair 1985) and to natural language processing (Baker 1979; Ferguson 1980; Garside et al. 1987; Sampson 1986; Sharman et al. 1988).”
Sphinx-4: a flexible open source framework for speech recognition (2004, methodology): “For example, Baker introduced hidde n Markov models (HMMs) with his Dragon system, [8], [10] and earlier predecessors of Sphinx explored variants of HMM s such as discrete HMMs [4], semicontinuous HMMs [5], and continuous HMMs [11].”
A time-delay neural network architecture for isolated word recognition (1990, background): “In the last few years, statistical recognition algorithms using hidden Markov models have replaced dynamic time warping as the dominant technology in speech recognition (Bahl, Jelinek, & Mercer, 1983, Baker, 1975 ).”