Applications of support vector machines to speech recognition

By Aravind Ganapathiraju, J. Hamaker, J. Picone. IEEE Transactions on Signal Processing, 2004

306 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ddacf4b9dea711d2ac50f0d6a29e62f3cd96bccb

How researchers see this paper

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

In Artificial Intelligence

1. Dong Yu
2. Tara N. Sainath
3. Bhuvana Ramabhadran
4. Jinyu Li
5. Michael A. Picheny
6. Li Deng
7. David Nahamoo
8. Jorge Luis Reyes-Ortiz

In Signal Processing

1. Tara N. Sainath
2. Dong Yu
3. Bhuvana Ramabhadran
4. Michael A. Picheny
5. Jinyu Li
6. David Nahamoo
7. Jorge Luis Reyes-Ortiz
8. Georgios B. Giannakis

Citations in the corpus

• Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR (2011, methodology): “While GMMs allow for fast model training and scoring, training samples are pooled together for parameter estimation, resulting in a loss of the information that exists within the individual training samples.”
• Consensus-Based Distributed Support Vector Machines (2010, background): “…classification tasks emerging inappl cations such as medical imaging, bio-informatics, speech, and handwriting recognition, to name a few (Vapnik, 1998; Scḧolkopf and Smola, 2002; El-Naqa et al., 2002; Liang et al., 2007; Ganapathiraju et al., 2004; Li, 2005; Markowska-Kaczmar and Kubacki, 2005).”
• Characterization of four-class motor imagery EEG data for the BCI-competition 2005 (2005, unknown): “…is a strong classification method which has demonstrated its excellent generalization property in various applications, e.g. the object recognition from an image (Osuna et al 1997), the classificationofhandwrittencharacters(OliveiraandSabourin 2004)andthespeechrecognition(Ganapathiraju et al 2004).”
• Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review (2020, background): “hypertext categorization [34], image detection, verification, and recognition [35], speech recognition [36], bankruptcy prediction [37], remote sensing image”
• Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine (2012, methodology): “Although it is not fully clear which method performs better for AR, SVMs have confirmed successful application in several areas including heterogeneous types of recognition such as handwritten characters [9] and speech [10].”