Speech Recognition with Weighted Finite-State Transducers

Mohri, Mehryar; Pereira, Fernando; Riley, Michael

doi:10.1007/978-3-540-49127-9_28

Cited by 199 publications

(139 citation statements)

References 26 publications

Supporting

Mentioning

139

Contrasting

Order By: Relevance

“…The search network is represented using WFSTs which is a state machine consisting of states and transitions between them [19]. Each transition has input and output symbols with weights.…”

Section: Search Networkmentioning

confidence: 99%

Efficient acoustic detector of gunshots and glass breaking

Lojka

Pleva

Kiktová

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

An efficient acoustic events detection system EAR-TUKE is presented in this paper. The system is capable of processing continuous input audio stream in order to detect potentially dangerous acoustic events, specifically gunshots or breaking glass. The system is programmed entirely in C++ language (core math. functions in C) and was designed to be self sufficient without requiring additional dependencies. In the design and development process the main focus was put on easy support of new acoustic events detection, low memory profile, low computational requirements to operate on devices with low resources, and on long-term operation and continuous input stream monitoring without any maintenance. In order to satisfy these requirements on the system, EAR-TUKE is based on a custom approach to detection and classification of acoustic events. The system is using acoustic models of events based on Hidden Markov Models (HMMs) and a modified Viterbi decoding process with an additional module to allow continuous monitoring. Cepstral Mean Normalization (CMN) and our proposed removal of basic coefficients from feature vectors to increase robustness. This paper also presents the development process and results evaluating the final design of the system.

show abstract

“…The search network is represented using WFSTs which is a state machine consisting of states and transitions between them [19]. Each transition has input and output symbols with weights.…”

Section: Search Networkmentioning

confidence: 99%

Efficient acoustic detector of gunshots and glass breaking

Lojka

Pleva

Kiktová

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…We use a dynamic network decoder based on weighted finitestate transducers (WFST) [10], which integrates the LM dynamically as needed during recognition. The composition of the language model transducer G and the lexicon transducer L is computed on demand using composition filters for on-thefly pushing of labels and weights [11].…”

Section: Decoding Using Wfstmentioning

confidence: 99%

Open vocabulary handwriting recognition using combined word-level and character-level language models

Kozielski

Rybach

Hahn

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

In this paper, we present a unified search strategy for open vocabulary handwriting recognition using weighted finite state transducers. Additionally to a standard word-level language model we introduce a separate n-gram character-level language model for out-of-vocabulary word detection and recognition. The probabilities assigned by those two models are combined into one Bayes decision rule. We evaluate the proposed method on the IAM database of English handwriting. An improvement from 22.2% word error rate to 17.3% is achieved comparing to the closed-vocabulary scenario and the best published result.

show abstract

“…The WFSTs allow composition, unification and concatenation of the transducers (for more details, see Mohri et al, 1997). In order to build up a WFST for the complete loc earthquake we simply concatenate the transducer for the first, second, and third loc state into one overall loc earthquake transducer.…”

Section: Weighted Finite-state Transducer Decodingmentioning

confidence: 99%

“…The authors wish to thank Heiner Igel for his kind support. We also wish to thank the authors of the HMM Tool Kit (HTK), Young et al (2002), the authors of the HMM-based Speech Synthesis System (HTS), Zen et al (2009) and the authors of the AT&T FSM Library TM , Mohri et al (1997) for providing and developing such powerful software packages. The suggestions of three referees, Wu Ye and two anonymous reviewers, substantially improved the manuscript.…”

mentioning

confidence: 99%

Hidden semi-Markov Model based earthquake classification system using Weighted Finite-State Transducers

Beyreuther

Wassermann

2011

Nonlin. Processes Geophys.

View full text Add to dashboard Cite

Abstract. Automatic earthquake detection and classification is required for efficient analysis of large seismic datasets. Such techniques are particularly important now because access to measures of ground motion is nearly unlimited and the target waveforms (earthquakes) are often hard to detect and classify. Here, we propose to use models from speech synthesis which extend the double stochastic models from speech recognition by integrating a more realistic duration of the target waveforms. The method, which has general applicability, is applied to earthquake detection and classification. First, we generate characteristic functions from the time-series. The Hidden semi-Markov Models are estimated from the characteristic functions and Weighted Finite-State Transducers are constructed for the classification. We test our scheme on one month of continuous seismic data, which corresponds to 370 151 classifications, showing that incorporating the time dependency explicitly in the models significantly improves the results compared to Hidden Markov Models.

show abstract

Speech Recognition with Weighted Finite-State Transducers

Cited by 199 publications

References 26 publications

Efficient acoustic detector of gunshots and glass breaking

Efficient acoustic detector of gunshots and glass breaking

Open vocabulary handwriting recognition using combined word-level and character-level language models

Hidden semi-Markov Model based earthquake classification system using Weighted Finite-State Transducers

Contact Info

Product

Resources

About