Unsupervised Speaker Indexing of Discussions Using Anchor Models

Yuya Akita; Tatsuya Kawahara

首页> 外文期刊>Systems and Computers in Japan >Unsupervised Speaker Indexing of Discussions Using Anchor Models

【24h】

Unsupervised Speaker Indexing of Discussions Using Anchor Models

机译：使用主持人模型的讨论的无监督发言人索引

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

We present unsupervised speaker indexing, combined with automatic speech recognition (ASR) for speech archives, such as discussions. Our proposed indexing method is based on anchor models, by which we define a feature vector based on the similarity with speakers of a large-scale speech database. We introduce dimensional normalization and reduction on the vectors to improve discriminant ability. These vectors are then clustered and initial speaker labels are obtained. Using the initial labels, speaker models are constructed for respective clusters and the speakers are finally indexed with the speaker models. We perform ASR using the results of this indexing. We achieved a speaker indexing accuracy of 91% and a significant improvement in the ASR for real discussion data.

机译：我们介绍了无监督的说话者索引，并结合了语音存档（例如讨论）的自动语音识别（ASR）。我们提出的索引方法基于锚模型，通过锚模型，我们基于与大型语音数据库说话者的相似性来定义特征向量。我们在向量上引入尺寸归一化和归约以提高判别能力。然后将这些向量聚类，并获得初始说话者标签。使用初始标签，为各个群集构建扬声器模型，并最终用扬声器模型对扬声器进行索引。我们使用此索引结果执行ASR。我们的发言人索引准确度达到91％，并且在实际讨论数据方面的ASR有了显着提高。

著录项

来源
《Systems and Computers in Japan》 |2005年第9期|共9页
作者
Yuya Akita; Tatsuya Kawahara;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类计算技术、计算机技术;
关键词
Speaker Recognition; Unsupervised Speaker Indexing; Discussion Speech; Anchor Models; Speech Recognition;

机译：说话人识别;无监督说话人索引;讨论语音;锚模型;语音识别;

相似文献

外文文献
中文文献
专利

1. Unsupervised Speaker Indexing of Discussions Using Anchor Models [J] . Yuya Akita, Tatsuya Kawahara Systems and Computers in Japan . 2005,第9期

机译：使用主持人模型的讨论的无监督发言人索引
2. Speaker indexing based on speaker model selection and automatic speech recognition in discussions [J] . Masafumi Nishida, Yuya Akita, Tatsuya Kawahara 電子情報通信学会技術研究報告. 言語理解とコミュニケーション. Natural Language Understanding and Models of Communication . 2002,第528期

机译：讨论中基于说话人模型选择和自动语音识别的说话人索引
3. Speaker indexing based on speaker model selection and automatic speech recognition in discussions [J] . Masafumi Nishida, Yuya Akita, Tatsuya Kawahara 電子情報通信学会技術研究報告. 音声. Speech . 2002,第530期

机译：基于扬声器模型选择和讨论中的自动语音识别的扬声器索引
4. Unsupervised Speaker Indexing using Anchor Models and Automatic Transcription of Discussions [C] . Yuya Akita, Tatsuya Kawahara, International Speech Communication Association(ISCA) European Conference on Speech Communication and Technology . 2003

机译：使用锚模型和讨论自动转录无监督的扬声器索引
5. A study of unsupervised speaker indexing. [D] . Kwon, Soon-Il. 2005

机译：无监督说话者索引研究。
6. Unsupervised Mining of Frequent Tags for Clinical Eligibility Text Indexing [O] . Riccardo Miotto, Chunhua Weng -1

机译：用于临床资格文本索引的频繁标签的无监督挖掘
7. Speaker model selection based on the Bayesian information criterion applied to unsupervised speaker indexing [O] . Nishida M., Kawahara T. 2005

机译：基于贝叶斯信息准则的说话人模型选择应用于无监督说话人索引
8. Speaker Indexing in Large Audio Databases Using Anchor Models [R] . Sturim, D. E., Reynolds, D. A., Singer, E., 2001

机译：使用锚模型在大型音频数据库中进行扬声器索引

Unsupervised Speaker Indexing of Discussions Using Anchor Models

摘要

著录项

相似文献

相关主题

期刊订阅