IMPACT OF DYNAMIC MODEL ADAPTATION BEYOND SPEECH RECOGNITION

被引：0

作者：

Batista, Fernando ^{[1
]}

Amaral, Rui ^{[1
]}

Trancoso, Isabel ^{[1
]}

Mamede, Nuno ^{[1
]}

机构：

[1] INESC ID Lisboa, L2F Spoken Language Syst Lab, P-1000029 Lisbon, Portugal

来源：

2008 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY: SLT 2008, PROCEEDINGS | 2008年

关键词：

Speech processing; Speech intelligibility; Natural language interfaces; Language Dynamics; Unsupervised learning;

D O I：

10.1109/SLT.2008.4777894

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The application of speech recognition to live subtitling of Broadcast News has motivated the adaptation of the lexical and language models of the recognizer on a daily basis with text material retrieved from online newspapers. This paper studies the impact of this adaptation on two of the blocks following the speech recognition module: capitalization and topic indexation. We describe and evaluate different adaptation approaches that try to explore the language dynamics.

引用

页码：277 / 280

页数：4

共 50 条

[21] Model adaptation based on HMM decomposition for reverberant speech recognition
Takiguchi, T
Nakamura, S
Huo, Q
Shikano, K
1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 827 - 830
[22] Automatic speech recognition with an adaptation model motivated by auditory processing
Holmberg, M
Gelbart, D
Hemmert, W
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (01): : 43 - 49
[23] An online model adaptation method for compensating speech models for noise in continuous speech recognition
Lee, R
Choi, EHC
ASRU 2001: IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, CONFERENCE PROCEEDINGS, 2001, : 147 - 150
[24] Unsupervised cross-adaptation approach for speech recognition by combined language model and acoustic model adaptation
School of Science and Engineering, Yamagata University, Yonezawa, Japan
APSIPA ASC - Asia-Pac. Signal Inf. Process. Assoc. Annu. Summit Conf., (943-946):
[25] On the Adaptation of Foreign Language Speech Recognition Engines for Lithuanian Speech Recognition
Rudzionis, Vytautas
Maskeliunas, Rytis
Rudzionis, Algimantas
Ratkevicius, Kastytis
BUSINESS INFORMATION SYSTEMS WORKSHOPS, 2009, 37 : 113 - +
[26] Model Adaptation Based on Improved Variance Estimation for Robust Speech Recognition
Lu, Yong
Xu, Zongyu
Yan, Qin
Zhou, Lin
2012 INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP 2012), 2012,
[27] Attention-based Contextual Language Model Adaptation for Speech Recognition
Martinez, Richard Diehl
Novotney, Scott
Bulyko, Ivan
Rastrow, Ariya
Stolcke, Andreas
Gandhe, Ankur
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 1994 - 2003
[28] Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition
Li, Ke
Xu, Hainan
Wang, Yiming
Povey, Daniel
Khudanpur, Sanjeev
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3373 - 3377
[29] Language Model Adaptation for Emotional Speech Recognition using Tweet data
Saeki, Kazuya
Kato, Masaharu
Kosaka, Tetsuo
2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 371 - 375
[30] TWO-STEP ACOUSTIC MODEL ADAPTATION FOR DYSARTHRIC SPEECH RECOGNITION
Takashima, Ryoichi
Takiguchi, Tetsuya
Ariki, Yasuo
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 6104 - 6108

← 1 2 3 4 5 →