Prosody Boundary Detection through Context-Dependent Position Models

被引:0
|
作者
Hu, Yue-Ning [1 ]
Chu, Min [2 ]
Huang, Chao [2 ]
Zhang, Yan-Ning [1 ]
机构
[1] Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shaanxi, Peoples R China
[2] Microsoft Res Asia, Beijing 100080, Peoples R China
来源
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | 2008年
关键词
Boundary detection; context-dependent position model; prosodic word; phrase;
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
In this paper, we propose to convert the prosody boundary detection task into a syllable position labeling task. In order to detect both prosodic word and prosodic phrase boundaries, 6 types of syllable positions are defined. For each position, context-dependent position models are trained from manually labeled data. These models are used to label syllable positions in unseen speech. Word and phrase boundaries are then easily derived from syllable position labels. The proposed approach is tested with a large scale single speaker database. The precision and recall for word boundary are 96.1% and 90.1%, respectively, and for phrase boundary arc 83.7% and 80.5%, respectively. Results of a listening test shows that only 28% of word boundaries and 50% of phrase of boundaries detected automatically are critical error, implying only about 2.2% and 10% errors for word and phrase boundaries, respectively. The results are rather good, especially when it is considered that only acoustic features are used in this work.
引用
收藏
页码:2142 / +
页数:2
相关论文
共 50 条
  • [1] PROSODY STUDY WITH CONTEXT-DEPENDENT ACOUSTIC MODELS
    Hu, Yue-Ning
    Chu, Min
    2008 6TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2008, : 57 - 60
  • [2] Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models
    Vaska, Nathan
    Leahy, Kevin
    Helus, Victoria
    2022 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2022, : 2020 - 2027
  • [3] Improved landmine detection through context-dependent score calibration
    Smock, Brandon
    Wilson, Joseph
    Milner, Martin
    SIGNAL PROCESSING, SENSOR/INFORMATION FUSION, AND TARGET RECOGNITION XXV, 2016, 9842
  • [4] Context-dependent factored language models
    Gregor Donaj
    Zdravko Kačič
    EURASIP Journal on Audio, Speech, and Music Processing, 2017
  • [5] Context-dependent factored language models
    Donaj, Gregor
    Kacic, Zdravko
    EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2017, : 1 - 16
  • [6] Reasoning on Context-Dependent Domain Models
    Boehme, Stephan
    Kuehn, Thomas
    SEMANTIC TECHNOLOGY, JIST 2017, 2017, 10675 : 69 - 85
  • [7] Phone Boundary Detection using Selective Refinements and Context-dependent Acoustic Features
    Boonsuk, Sirinoot
    Punyabukkana, Proadpran
    Suchato, Atiwong
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2912 - 2915
  • [8] Context-dependent sound event detection
    Toni Heittola
    Annamaria Mesaros
    Antti Eronen
    Tuomas Virtanen
    EURASIP Journal on Audio, Speech, and Music Processing, 2013
  • [9] Context-dependent sound event detection
    Heittola, Toni
    Mesaros, Annamaria
    Eronen, Antti
    Virtanen, Tuomas
    EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2013,
  • [10] Context-dependent substitution models for circular DNA
    Zhang, Rongli
    Yap, Von Bing
    INFECTION GENETICS AND EVOLUTION, 2013, 18 : 362 - 366