BOOKS ON TAPE AS TRAINING DATA FOR CONTINUOUS SPEECH RECOGNITION

被引：2

作者：

BOULIANNE, G ^{[1
]}

KENNY, P ^{[1
]}

LENNIG, M ^{[1
]}

OSHAUGHNESSY, D ^{[1
]}

MERMELSTEIN, P ^{[1
]}

机构：

[1] BELL NO RES LTD, MONTREAL, PQ, CANADA

来源：

SPEECH COMMUNICATION | 1994年 / 14卷 / 01期

关键词：

HIDDEN MARKOV MODEL; CONTINUOUS SPEECH RECOGNITION; TRAINING ALGORITHM; SPEECH SEGMENTATION; SPEECH LABELING; VITERBI DECODING;

D O I：

10.1016/0167-6393(94)90057-4

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Training algorithms for natural speech recognition require very large amounts of transcribed speech data. Commercially distributed books on tape constitute an abundant source of such data, but it is difficult to take advantage of it using current training algorithms because of the requirement that the data be hand-segmented into chunks that can be comfortably processed in memory. In order to address this problem we have developed a training algorithm which is capable of handling unsegmented data files of arbitrary length; the computational requirements of the algorithm are linear in the amount of data to be processed and the memory requirements are constant.

引用

页码：61 / 70

页数：10

共 50 条

[1] EXPERIMENTS IN CONTINUOUS SPEECH RECOGNITION USING BOOKS ON TAPE
KENNY, P
BOULIANNE, G
GARUDADRI, H
TRUDELLE, S
HOLLAN, R
LENNIG, M
OSHAUGHNESSY, D
[J]. SPEECH COMMUNICATION, 1994, 14 (01) : 49 - 60
[2] Validation of Speech Data for Training Automatic Speech Recognition Systems
Krizaj, Janes
Gros, Jerneja Zganec
Dobrisek, Simon
[J]. 2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022), 2022, : 1165 - 1169
[3] Description of training procedure for AlfaNum continuous speech recognition system
Jakovljevic, N
Pekar, D
[J]. Eurocon 2005: The International Conference on Computer as a Tool, Vol 1 and 2 , Proceedings, 2005, : 1646 - 1649
[4] Task independent minimum confusibility training for continuous speech recognition
Nogueiras-Rodriguez, A
Marino, JB
[J]. PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 477 - 480
[5] Utterance verification in continuous speech recognition: Decoding and training procedures
Lleida, E
Rose, RC
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2000, 8 (02): : 126 - 139
[6] Speaker selection training for large vocabulary continuous speech recognition
Huang, C
Chen, T
Chang, E
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 609 - 612
[7] DATA DRIVEN SEARCH ORGANIZATION FOR CONTINUOUS SPEECH RECOGNITION
NEY, H
MERGEL, D
NOLL, A
PAESELER, A
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (02) : 272 - 281
[8] CONTINUOUS SPEECH RECOGNITION
MORGAN, N
BOURLARD, H
[J]. IEEE SIGNAL PROCESSING MAGAZINE, 1995, 12 (03) : 25 - 42
[9] Efficient decoding and training procedures for utterance verification in continuous speech recognition
Lleida, E
Rose, RC
[J]. 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 507 - 510
[10] Features extraction and training strategies in continuous speech recognition for Romanian language
Dumitru, Corneliu Octavian
Gavat, Inge
[J]. ICINCO 2006: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS: SIGNAL PROCESSING, SYSTEMS MODELING AND CONTROL, 2006, : 114 - 121

← 1 2 3 4 5 →