A Spoken Term Detection Framework for Recovering Out-of-Vocabulary Words Using the Web

被引：0

作者：

Parada, Carolina ^{[1
]}

Sethy, Abhinav ^{[2
]}

Dredze, Mark ^{[1
]}

Jelinek, Frederick ^{[1
]}

机构：

[1] Johns Hopkins Univ, Ctr Language & Speech Proc, Human Language Technol Ctr Excellence, 3400 N Charles St, Baltimore, MD 21210 USA

[2] IBM TJ Watson Res Ctr, New York, NY 10598 USA

来源：

11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2 | 2010年

关键词：

language modeling; data selection; spoken term detection; oov detection;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Vocabulary restrictions in large vocabulary continuous speech recognition (LVCSR) systems mean that out-of-vocabulary (OOV) words are lost in the output. However, OOV words tend to be information rich terms (often named entities) and their omission from the transcript negatively affects both usability and downstream NLP technologies, such as machine translation or knowledge distillation. We propose a novel approach to OOV recovery that uses a spoken term detection (STD) framework. Given an identified OOV region in the LVCSR output, we recover the uttered OOVs by utilizing contextual information and the vast and constantly updated vocabulary on the Web. Discovered words are integrated into system output, recovering up to 40% of OOVs and resulting in a reduction in system error.

引用

页码：1269 / +

页数：2

共 50 条

[21] WASSUP? LOL : Characterizing Out-of-Vocabulary Words in Twitter
Maity, Suman Kalyan
Chaudhary, Anshit
Kumar, Shraman
Mukherjee, Animesh
Sarda, Chaitanya
Patil, Abhijeet
Mondal, Akash
PROCEEDINGS OF THE 19TH ACM CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING COMPANION, 2016, : 341 - 344
[22] Handling Out-of-Vocabulary Words in Lexicons to Polarity Classification
Nascimento, Gabriel
Duarte, Fellipe
Guedes, Gustavo Paiva
PROCEEDINGS OF THE 17TH BRAZILIAN SYMPOSIUM ON HUMAN FACTORS IN COMPUTING SYSTEMS (IHC 2018), 2015,
[23] COPING WITH OUT-OF-VOCABULARY WORDS: OPEN VERSUS HUGE VOCABULARY ASR
Gerosa, Matteo
Federico, Marcello
2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 4313 - 4316
[24] Similarity Scoring for Recognizing Repeated Out-of-Vocabulary Words
Hannemann, Mirko
Kombrink, Stefan
Karafiat, Martin
Burget, Lukas
11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 897 - 900
[25] A category based approach for recognition of out-of-vocabulary words
Gallwitz, F
Noth, E
Niemann, H
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 228 - 231
[26] Recurrent Out-of-Vocabulary Word Detection Using Distribution of Features
Asami, Taichi
Masumura, Ryo
Aono, Yushi
Shinoda, Koichi
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1320 - 1324
[27] Out-of-Vocabulary Word Detection in Spoken Dialogues Based on Joint Decoding with User Response Patterns
Oshio, Miki
Munakata, Hokuto
Takeda, Ryu
Komatani, Kazunori
2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 1753 - 1759
[28] SPEECH RECOGNITION OF FOREIGN OUT-OF-VOCABULARY WORDS USING A HIERARCHICAL LANGUAGE MODEL
Yamamoto, Hirofumi
Kikui, Genichiro
Nakamura, Satoshi
Sagisaka, Yoshinori
INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1870 - +
[29] Impact of Out-of-Vocabulary Words on the Twitter Experience of Blind Users
Lee, Hae-Na
Ashok, Vikas
PROCEEDINGS OF THE 2022 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI' 22), 2022,
[30] Improving Abstractive Summarization by Training Masked Out-of-Vocabulary Words
Lee, Tae-Seok
Lee, Hyun-Young
Kang, Seung-Shik
JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2022, 18 (03): : 344 - 358

← 1 2 3 4 5 →