The forward-backward search algorithm

Austin, S.; Schwartz, Richard; Placeway, Paul

doi:10.1109/icassp.1991.150435

Cited by 74 publications

(32 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decoding is done by the two-pass (forward and backward) beam search [1,19]. In addition, we use a trigram language model to guide the path search in which the probabilities of all triplets of words in the training dataset are computed.…”

Section: Hmm Recognitionmentioning

confidence: 99%

“…Due to the complexity of the raw signal, handwriting recognition systems usually work on discrete features extracted from the raw signal. In addition, feature transform is employed for the following two reasons: (1) to resolve the correlation between dimensions of features. (2) to alleviate the data sparsity problem in a high dimensional space by forcing discriminating power into fewer dimensions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Applying Discriminatively Optimized Feature Transform for HMM-based Off-Line Handwriting Recognition

Chen

Zhang

Cao

et al. 2012

2012 International Conference on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

Feature extraction is an important step in off-line handwriting recognition systems to represent raw handwriting in a low-dimensional, tractable feature space. Traditionally, linear feature transforms such as Principle Component Analysis (PCA), Linear Discriminative Analysis (LDA) are commonly used. The assumptions they make, however, usually cannot be satisfied in practice and thus the best performance is not obtained. In this paper, we apply the Region-Dependent nonlinear feature Transform (RDT) to handwriting recognition. RDT is one type of non-linear feature transforms which captures the discriminating power much better than traditional linear ones. We justify the effectiveness of RDT on handwriting features using an HMM-based handwriting recognition system on an Arabic handwriting dataset, which consists of 38K pages of handwriting, over 3M handwritten words. Experimental results show that RDT is able to decrease the word error rates (WERs) relatively by 4% to 7% with statistical significance, comparing to two LDA-based baseline systems. * Jin Chen performed this work during his summer internship at Raytheon BBN Technologies.

show abstract

Section: Hmm Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Applying Discriminatively Optimized Feature Transform for HMM-based Off-Line Handwriting Recognition

Chen

Zhang

Cao

et al. 2012

2012 International Conference on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

show abstract

“…There have been very few attempts at automatically detecting the presence of new words, with limited success (39). Most (40)(41)(42)(43)(44). In addition, computing advances have achieved two-orders-magnitude increase in workstation Proc.…”

Section: Hidden Markov Modelsmentioning

confidence: 99%

State of the art in continuous speech recognition.

Makhoul¹,

Schwartz²

1995

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

In the past decade, tremendous advances in the state of the art of automatic speech recognition by machine have taken place. A reduction in the word error rate by more than a factor of 5 and an increase in recognition speeds by several orders of magnitude (brought about by a combination of faster recognition search algorithms and more powerful computers), have combined to make high-accuracy, speakerindependent, continuous speech recognition for large vocabularies possible in real time, on off-the-shelf workstations, without the aid of special hardware. These advances promise to make speech recognition technology readily available to the general public. This paper focuses on the speech recognition advances made through better speech modeling techniques, chiefly through more accurate mathematical modeling of speech sounds.More and more, speech recognition technology is making its way from the laboratory to real-world applications. Recently, a qualitative change in the state of the art has emerged that promises to bring speech recognition capabilities within the reach of anyone with access to a workstation. High-accuracy, real-time, speaker-independent, continuous speech recognition for medium-sized vocabularies (a few thousand words) is now possible in software on off-the-shelf workstations. Users will be able to tailor recognition capabilities to their own applications. Such software-based, real-time solutions usher in a whole new era in the development and utility of speech recognition technology.As is often the case in technology, a paradigm shift occurs when several developments converge to make a new capability possible. In the case of continuous speech recognition, the following advances have converged to make the new technology possible: * higher-accuracy continuous speech recognition, based on better speech modeling techniques; * better recognition search strategies that reduce the time needed for high-accuracy recognition; and * increased power of audio-capable, off-the-shelf workstations. The paradigm shift is taking place in the way we view and use speech recognition. Rather than being mostly a laboratory endeavor, speech recognition is fast becoming a technology that is pervasive and will have a profound influence on the way humans communicate with machines and with each other. This paper focuses on speech modeling advances in continuous speech recognition, with an exposition of hidden Markov models (HMMs), the mathematical backbone behind these advances. While knowledge of properties of the speech signal and of speech perception have always played a role, recent improvements have relied largely on solid mathematical and probabilistic modeling methods, especially the use of HMMs for modeling speech sounds. These methods are capable of modeling time and spectral variability simultaneously, and the model parameters can be estimated automatically from given training speech data. The traditional processes of segmentation and labeling of speech sounds are now merged into a single probabilistic proce...

show abstract

“…A forward pass with a bigram grammar and discrete HMM models saves the top word-ending scores and times [6].…”

Section: Byblosmentioning

confidence: 99%

Comparative experiments on large vocabulary speech recognition

Schwartz¹,

Anastasakos²,

Kubala³

et al. 1993

Proceedings of the Workshop on Human Language Technology - HLT '93

View full text Add to dashboard Cite

This paper describes several key experiments in large vocabulay speech recognition. We demonstrate that, counter to our intuitions, given a fixed amount of training speech, the number of training speakers has little effect on the accuracy. We show how much speech is needed for speaker-independent (SI) recognition in order to achieve the same performance as speakerdependent (SD) recognition. We demonstrate that, though the N-Best Paradigm works quite well up to vocabularies of 5,000 words, it begins to break down with 20,000 words and long sentences. We compare the performance of two feature preprocessing algorithms for microphone independence and we describe a new microphone adaptation algorithm based on selection among several codebook transformations.

show abstract

The forward-backward search algorithm

Cited by 74 publications

References 4 publications

Applying Discriminatively Optimized Feature Transform for HMM-based Off-Line Handwriting Recognition

Applying Discriminatively Optimized Feature Transform for HMM-based Off-Line Handwriting Recognition

State of the art in continuous speech recognition.

Comparative experiments on large vocabulary speech recognition

Contact Info

Product

Resources

About