Importance of High-Order N-Gram Models in Morph-Based Speech Recognition

Hirsimäki, Teemu; Pylkkönen, Janne; Kurimo, Mikko

doi:10.1109/tasl.2008.2012323

Cited by 80 publications

(59 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…N-gram models are widely used in statistical natural language processing and speech recognition. An ngram is a sub-sequence of n overlapping items (characters, letters, words, etc) from a given sequence [15][16]. For example, the result of the application of 2-gram character model to the string "benign" is "be", "en", "ni", "ig", "gn".…”

Section: B N-gram Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Unknown Malware on Android by Machine Learning Using the Feature of Dalvik Operation Code

Wang¹,

Li²,

Zheng³

et al. 2017

Proceedings of the 2017 2nd International Conference on Automatic Control and Information Engineering (ICACIE 2017)

View full text Add to dashboard Cite

Abstract-The recent growth in network usage has motivated the creation of new malicious code for various purposes, including economic ones. Today's signature-based anti-viruses are very accurate, but cannot detect new malicious code. Recently, classification algorithms were employed successfully for the detection of unknown malicious code. However, most of the studies use byte sequence n-gram representation of the binary code of the executable files on windows. We propose the use of Dalvik Operation Code on Android, generated by disassembling the application. We then use n-gram of the operation code as features for the classification process. We present a full methodology for the detection of unknown malicious code, based on text categorization concepts. The experiment results show that the method results are in a high accuracy rate.

show abstract

Section: B N-gram Modelsmentioning

confidence: 99%

“…[15] The extension combines Breiman's "bagging" idea and random selection of features, introduced first by Ho [1] and later independently by Amit and Geman [16] in order to construct a collection of decision trees with controlled variance.…”

Section: A Random Forestmentioning

confidence: 99%

Detecting Unknown Malware on Android by Machine Learning Using the Feature of Dalvik Operation Code

Wang¹,

Li²,

Zheng³

et al. 2017

Proceedings of the 2017 2nd International Conference on Automatic Control and Information Engineering (ICACIE 2017)

View full text Add to dashboard Cite

show abstract

“…Acoustic model parameters are trained on 30-hours of data drawn from the Finnish SPEECON database, consisting of clean speech utterances recorded with a headset in quiet environments (SNR 16-44 dB). The decoder is a time-synchronous beam-pruned Viterbi token-pass system, and the language model is a morph-based growing n-gram model (Hirsimäki et al, 2009) trained on Finnish book and newspaper data with 145 million words. The vocabulary is in practice unlimited, since all words and word forms can be represented with statistical morphs (Hirsimäki et al, 2006).…”

Section: Baseline Systemmentioning

confidence: 99%

Comparing human and automatic speech recognition in a perceptual restoration experiment

Remes

López

Juvela

et al. 2016

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

Speech that has been distorted by introducing spectral or temporal gaps is still perceived as continuous and complete by human listeners, so long as the gaps are filled with additive noise of sufficient intensity. When such perceptual restoration occurs, the speech is also more intelligible compared to the case in which noise has not been added in the gaps. This observation has motivated so-called 'missing data' systems for automatic speech recognition (ASR), but there have been few attempts to determine whether such systems are a good model of perceptual restoration in human listeners. Accordingly, the current paper evaluates missing data ASR in a perceptual restoration task. We evaluated two systems that use a new approach to bounded marginalisation in the cepstral domain, and a bounded conditional mean imputation method. Both methods model available speech information as a clean-speech posterior distribution that is subsequently passed to an ASR system. The proposed missing data ASR systems were evaluated using distorted speech, in which spectro-temporal gaps were optionally filled with additive noise. Speech recognition performance of the proposed systems was compared against a baseline ASR system, and with human speech recognition performance on the same task. We conclude that missing data methods improve speech recognition performance in a manner that is consistent with perceptual restoration in human listeners.

show abstract

“…An n-gram is a sub-sequence of n overlapping items (characters, letters, words, etc) from a given sequence [16]. N-gram sequences are then used to construct n-gram frequency vectors, which express the frequency of appearance of every n-byte and n-opcode.…”

Section: Feature Extractionmentioning

confidence: 99%

Support vector machine integrated with game-theoretic approach and genetic algorithm for the detection and classification of malware

Zolotukhin

Hämäläinen

2013

2013 IEEE Globecom Workshops (GC Wkshps)

View full text Add to dashboard Cite

Importance of High-Order N-Gram Models in Morph-Based Speech Recognition

Cited by 80 publications

References 25 publications

Detecting Unknown Malware on Android by Machine Learning Using the Feature of Dalvik Operation Code

Detecting Unknown Malware on Android by Machine Learning Using the Feature of Dalvik Operation Code

Comparing human and automatic speech recognition in a perceptual restoration experiment

Support vector machine integrated with game-theoretic approach and genetic algorithm for the detection and classification of malware

Contact Info

Product

Resources

About