Spoken Language Processing

By A. Acero, Xuedong Huang, Hsiao-Wuen Hon. 2001

998 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e87cda5c74dffd35c438b76ccc57394ff4b9d218

How researchers see this paper

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

Citations in the corpus

Introduction to Digital Speech Processing (2007, methodology): “The details of the Baum–Welch procedure are beyond the scope of this chapter but can be found in several references on Speech Recognition methods [49, 99].”
Graphical Models, Exponential Families, and Variational Inference (2008, background): “Large-scale systems are built by composing elementary HMMs into larger graphical models.”
Social signal processing: Survey of an emerging domain (2009, methodology): “The measurement of the pitch, often called fundamental frequency (or F0) because most of the speech energy is concentrated over components corresponding to its integer multiples, can be performed with several standard methods proposed in the literature [84][156].”
Hierarchical Dirichlet Processes (2006, background): “…examples of applications of finite mixtures and their dynamical cousins the HMMs in such areas as bioinformatics (Durbin, Eddy, Krogh, and Mitchison 1998), speech recognition (Huang, Acero, and Hon 2001), information retrieval (Blei et al. 2003), and computational vision (Forsyth and Ponce 2002).”
Text-informed speech enhancement with deep neural networks (2015, background): “To resolve this issue, a considerable amount of speech enhancement research has been done from various perspectives [1].”
Lexicon-Free Conversational Speech Recognition with Neural Networks (2015, background): “Building such systems is difﬁcult because spontaneous, conversational speech naturally contains repetitions, disﬂuencies, partial words, and out of vocabulary (OOV) words (De Mori et al., 2008; Huang et al., 2001).”
Use of Differential Cepstra as Acoustic Features in Hidden Trajectory Modeling for Phonetic Recognition (2007, methodology): “In the work presented in this paper, we generalize the earlier HTM by predicting not only the “static” cepstra but also the framedifferential cepstra (also known as dynamic or delta or regression features [7, 10, 22]).”
Bayesian Nonparametrics: Hierarchical Bayesian nonparametric models with applications (2010, unknown): “Speech recognition has been a major application area for classical parametric HMMs (Huang et al., 2001).”
Dynamic Speech Models: Theory, Algorithms, and Applications (2006, background): “Within the speech recognition community, researchers often refer to speech dynamics as differential or regression parameters derived from the acoustic vector sequence (called delta, delta–delta, or “dynamic” features) [4, 5].”
Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated Noise Suppressor (2008, methodology): “The CMN baseline is the system with the WI007 front-end and a standard active gain normalization [12] and cepstral mean normalization algorithm (Fig.”
Discriminative learning in sequential pattern recognition (2008, unknown): “IEEE SIGNAL PROCESSING MAGAZINE [21] SEPTEMBER 2008 In (25), X 1 . . .”
Model-Based Approaches to Handling Uncertainty (2011, background): “If the component that generated the distribution at time t is known (here n̂t), then the MMSE estimate of the clean speech will be a linear transform of the corrupted speech [29] x̂t = E {x|yt , n̂t} (16) = μ (n̂t ) x +Σ (n̂t) xy Σ (n̂t)-1 y (yt − μ (n̂t) y ) (17) = At yt +b (n̂t) (18) In practice t”