A Mandarin dictation machine based upon a hierarchical recognition approach and Chinese natural language analysis

Lee, L.-S.; Tseng, Chiu‐yu; Chen, K.J.; Huang, Jen‐Yu; Hwang, Cheng-Wei; Ting, Pei‐Yih; Lin, Luke; Chen, C.C.

doi:10.1109/34.56213

Cited by 8 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This makes the present language processor not sensitive at all to the increased number of noisy word hypotheses in a very large vocabulary environment. An experimental system for Mandarin speech recognition has been implemented (Lee, 1990) and tested, in which a very high correct rate of recognition (93.8%) was obtained at a very high processing speed (about 5 sec per sentence on an IBM PC/AT). This indicates significant improvements as compared to previously proposed models.…”

mentioning

confidence: 99%

A preference-first language processor integrating the unification grammar and Markov language model for speech recognition applications

Chien

Chen

Lee

1991

Proceedings of the 29th Annual Meeting on Association for Computational Linguistics -

View full text Add to dashboard Cite

A language processor is to find out a most promising sentence hypothesis for a given word lattice obtained from acoustic signal recognition. In this paper a new language processor is proposed, in which unification granunar and Markov language model are integrated in a word lattice parsing algorithm based on an augmented chart, and the island-driven parsing concept is combined with various preference-first parsing strategies defined by different construction principles and decision rules. Test results"show that significant improvements in both correct rate of recognition and computation speed can be achieved .

show abstract

mentioning

confidence: 99%

A preference-first language processor integrating the unification grammar and Markov language model for speech recognition applications

Chien

Chen

Lee

1991

Proceedings of the 29th Annual Meeting on Association for Computational Linguistics -

View full text Add to dashboard Cite

show abstract

“…According to Shannon's work [21], Vector Quantization (VQ) provides better performance by coding vectors instead of scalars. In addition, VQ technique can be used to solve pattern recognition and data classification problems [13] ~31. 'Tb macarch was supported in p u t by NSF under grant IRI-9115810.…”

Section: Introductionmentioning

confidence: 99%

An architecture for tree search based vector quantization for single chip implementation

Park

Prasanna

Wang

[1992] Proceedings of the International Conference on Application Specific Array Processors

View full text Add to dashboard Cite

Vector Quantization (VQ) has become feasible to be used in d -t i m e applications by employing VLSZ technology. In this paper, we pmpose a new search algorithm and an ar-&tectum for implementing it, which mn be used in ml-time image processing. This search algorithm takes O(k) time units on a sequential machine, where k is the dimension of the deuectors, assuming unit time corresponds to one comparison opemtwn. The pmposed aditectum employs a single Processing Element (PE) and O ( N ) ezternal memory for storing N hyperplanes used in the search, where N is the number of codeuectors.C o m p a d with known amhitectures for VQ in the litenatum, the PFoPdped design does not perform any multiplication opemtwn, since the search method is independent of any L, metric, 1 5 q 5 00. Zt leads to an area eflcient design with the PE consisting of a compamtor and 00) nqisters. Also, the memory used by ihe design is significnntly lees than those employed in the known architectures.

show abstract

Crucial combinations of parts for handwritten alphanumeric characters

Suen

2000

Mathematical and Computer Modelling

View full text Add to dashboard Cite

A Mandarin dictation machine based upon a hierarchical recognition approach and Chinese natural language analysis

Cited by 8 publications

References 11 publications

A preference-first language processor integrating the unification grammar and Markov language model for speech recognition applications

A preference-first language processor integrating the unification grammar and Markov language model for speech recognition applications

An architecture for tree search based vector quantization for single chip implementation

Crucial combinations of parts for handwritten alphanumeric characters

Contact Info

Product

Resources

About