The search functionality is under construction.

The search functionality is under construction.

A duration modeling technique is proposed for the HMM based connected digit recognizer. The proposed duration modeling technique uses a cumulative duration probability. The cumulative duration probability is defined as the partial sum of the duration probabilities which can be estimated from the training speech data. Two approaches of using it are presented. First, the cumulative duration probability is used as a weighting factor to the state transition probability of HMM. Second, it replaces the conventional state transition probability. In both approaches, the cumulative duration probability is combined directly to the Viterbi decoding procedure. A modified Viterbi decoding procedure is also presented. One of the advantages of the proposed duration modeling technique is that the cumulative duration probability rules the transitions of states and words at each frame. Therefore, an additional post-procedure is not required. The proposed technique was examined by recognition experiments on Korean connected digit. Experimental results showed that two approach achieved almost same performances and that the average recognition accuracy was enhanced from 83.60% to 93.12%.

- Publication
- IEICE TRANSACTIONS on Information Vol.E85-D No.9 pp.1452-1454

- Publication Date
- 2002/09/01

- Publicized

- Online ISSN

- DOI

- Type of Manuscript
- LETTER

- Category
- Speech and Hearing

The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.

Copy

Tae-Young YANG, Chungyong LEE, Dae-Hee YOUN, "Duration Modeling Using Cumulative Duration Probability" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 9, pp. 1452-1454, September 2002, doi: .

Abstract: A duration modeling technique is proposed for the HMM based connected digit recognizer. The proposed duration modeling technique uses a cumulative duration probability. The cumulative duration probability is defined as the partial sum of the duration probabilities which can be estimated from the training speech data. Two approaches of using it are presented. First, the cumulative duration probability is used as a weighting factor to the state transition probability of HMM. Second, it replaces the conventional state transition probability. In both approaches, the cumulative duration probability is combined directly to the Viterbi decoding procedure. A modified Viterbi decoding procedure is also presented. One of the advantages of the proposed duration modeling technique is that the cumulative duration probability rules the transitions of states and words at each frame. Therefore, an additional post-procedure is not required. The proposed technique was examined by recognition experiments on Korean connected digit. Experimental results showed that two approach achieved almost same performances and that the average recognition accuracy was enhanced from 83.60% to 93.12%.

URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_9_1452/_p

Copy

@ARTICLE{e85-d_9_1452,

author={Tae-Young YANG, Chungyong LEE, Dae-Hee YOUN, },

journal={IEICE TRANSACTIONS on Information},

title={Duration Modeling Using Cumulative Duration Probability},

year={2002},

volume={E85-D},

number={9},

pages={1452-1454},

abstract={A duration modeling technique is proposed for the HMM based connected digit recognizer. The proposed duration modeling technique uses a cumulative duration probability. The cumulative duration probability is defined as the partial sum of the duration probabilities which can be estimated from the training speech data. Two approaches of using it are presented. First, the cumulative duration probability is used as a weighting factor to the state transition probability of HMM. Second, it replaces the conventional state transition probability. In both approaches, the cumulative duration probability is combined directly to the Viterbi decoding procedure. A modified Viterbi decoding procedure is also presented. One of the advantages of the proposed duration modeling technique is that the cumulative duration probability rules the transitions of states and words at each frame. Therefore, an additional post-procedure is not required. The proposed technique was examined by recognition experiments on Korean connected digit. Experimental results showed that two approach achieved almost same performances and that the average recognition accuracy was enhanced from 83.60% to 93.12%.},

keywords={},

doi={},

ISSN={},

month={September},}

Copy

TY - JOUR

TI - Duration Modeling Using Cumulative Duration Probability

T2 - IEICE TRANSACTIONS on Information

SP - 1452

EP - 1454

AU - Tae-Young YANG

AU - Chungyong LEE

AU - Dae-Hee YOUN

PY - 2002

DO -

JO - IEICE TRANSACTIONS on Information

SN -

VL - E85-D

IS - 9

JA - IEICE TRANSACTIONS on Information

Y1 - September 2002

AB - A duration modeling technique is proposed for the HMM based connected digit recognizer. The proposed duration modeling technique uses a cumulative duration probability. The cumulative duration probability is defined as the partial sum of the duration probabilities which can be estimated from the training speech data. Two approaches of using it are presented. First, the cumulative duration probability is used as a weighting factor to the state transition probability of HMM. Second, it replaces the conventional state transition probability. In both approaches, the cumulative duration probability is combined directly to the Viterbi decoding procedure. A modified Viterbi decoding procedure is also presented. One of the advantages of the proposed duration modeling technique is that the cumulative duration probability rules the transitions of states and words at each frame. Therefore, an additional post-procedure is not required. The proposed technique was examined by recognition experiments on Korean connected digit. Experimental results showed that two approach achieved almost same performances and that the average recognition accuracy was enhanced from 83.60% to 93.12%.

ER -