Spoken Language Processing: A Guide to Theory, Algorithm and System Development

By A. Acero, Alex Acero. 2001

853 citations recorded by the source corpus.

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

Visualizing and Understanding Recurrent Networks (2015, neutral): “This is a standard smoothing method for language models (15).”
A Tandem Algorithm for Pitch Estimation and Voiced Speech Segregation (2010, neutral): “Spectral sub-traction is a standard method for speech enhancement [21] (see also [16]).”
Analysis by Synthesis: A (Re-)Emerging Program of Research for Language and Vision (2010, neutral): “Thus, the array of apparent ‘direct perception’ devices and models has expanded greatly, and converge onto a high degree of success (Huang et al. 2001).”
Gaussian Processes for Signal Strength-Based Location Estimation (2006, neutral): “Here, n is the number of detected access points and γ ∈ [0 : 1] plays the role of a smoothing coefficient [6].”
Learning Speaker-Specific Characteristics With a Deep Neural Architecture (2011, neutral): “Vowels are believed to be the main carrier of SI and convey most of the information present in speech formants [43], [44].”
A Novel Connectionist System for Unconstrained Handwriting Recognition (2009, neutral): “This contrasts with HMMs, where the language model weighting factor must be found empirically because HMMs are known to underestimate acoustic scores [54].”
Graphical model architectures for speech recognition (2005, positive): “This article assumes some familiarity with basic speech-totext concepts [16], [ 25 ], [26], [42], [46], [47] and the basics of graphical models [28], [29], [32], [41], including notions such as hidden and observed variables, evidence, and factorization and conditional independence.”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, neutral): “Moreover, in training HMM-based ASR systems, parameter tying is often used as a type of regularization [25].”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, neutral): “All these representations are covered in speech processing textbooks [151] and implemented in standard toolkits such as Kaldi [277].”
Dynamic Graphical Models (2010, neutral): “Synchronous procedures have, for the most part, bested their asynchronous brethren perhaps due to their overall efficiency, simplicity, and performance [9].”
Challenges in adopting speech recognition (2004, neutral): “In general, noise-robust techniques can be classified into two categories: feature-space compensation and model-space compensation [4, 8].”
The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks (2019, neutral): “inspired model effectively performs similar signal processing steps as customary spoken language processing applications [46].”
Text-to-Speech Synthesis (2009, neutral): “General introductions to HMMs can be found in [243], [224].”