2009 IEEE Workshop on Automatic Speech Recognition & Understanding最新文献_第2页

Correlation-based query relaxation for example-based dialog modeling 基于关联的查询松弛，用于基于示例的对话建模

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373242

Cheongjae Lee, Sungjin Lee, Sangkeun Jung, Kyungduk Kim, Donghyeon Lee, G. G. Lee

引用次数: 13

Large-margin feature adaptation for automatic speech recognition 自动语音识别的大距特征自适应

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373320

Chih-Chieh Cheng, Fei Sha, L. Saul

引用次数: 4

Integrating prosodic features in extractive meeting summarization 结合节选会议摘要的韵律特征

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373302

Shasha Xie, Dilek Z. Hakkani-Tür, Benoit Favre, Yang Liu

引用次数: 56

Multilingual speaker age recognition: Regression analyses on the Lwazi corpus 多语说话者年龄识别:Lwazi语料库的回归分析

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373374

M. Feld, E. Barnard, C. V. Heerden, Christian A. Müller

{"title":"Multilingual speaker age recognition: Regression analyses on the Lwazi corpus","authors":"M. Feld, E. Barnard, C. V. Heerden, Christian A. Müller","doi":"10.1109/ASRU.2009.5373374","DOIUrl":"https://doi.org/10.1109/ASRU.2009.5373374","url":null,"abstract":"Multilinguality represents an area of significant opportunities for automatic speech-processing systems: whereas multilingual societies are commonplace, the majority of speech-processing systems are developed with a single language in mind. As a step towards improved understanding of multilingual speech processing, the current contribution investigates how an important para-linguistic aspect of speech, namely speaker age, depends on the language spoken. In particular, we study how certain speech features affect the performance of an age recognition system for different South African languages in the Lwazi corpus. By optimizing our feature set and performing language-specific tuning, we are working towards true multilingual classifiers. As they are closely related, ASR and dialog systems are likely to benefit from an improved classification of the speaker. In a comprehensive corpus analysis on long-term features, we have identified features that exhibit characteristic behaviors for particular languages. In a follow-up regression experiment, we confirm the suitability of our feature selection for age recognition and present cross-language error rates. The mean absolute error ranges between 7.7 and 12.8 years for same-language predictors and rises to 14.5 years for cross-language predictors.","PeriodicalId":292194,"journal":{"name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128285934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Leveraging speech production knowledge for improved speech recognition 利用语音生产知识来改进语音识别

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373368

A. Sangwan, J. Hansen

引用次数: 3

The exploration/exploitation trade-off in Reinforcement Learning for dialogue management 对话管理中强化学习的探索/利用权衡

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373260

S. Varges, G. Riccardi, S. Quarteroni, A. Ivanov

引用次数: 4

From speech to letters - using a novel neural network architecture for grapheme based ASR 从语音到字母——使用一种新颖的神经网络架构进行基于字素的ASR

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373257

F. Eyben, M. Wöllmer, Björn Schuller, Alex Graves

引用次数: 51

Ontology-based grounding of Spoken Language Understanding 基于本体的口语理解基础

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5373500

S. Quarteroni, Marco Dinarelli, G. Riccardi

引用次数: 2

Towards integrated machine translation using structural alignment from syntax-augmented synchronous parsing 从语法增强同步解析到使用结构对齐的集成机器翻译

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5372892

Bing Xiang, Bowen Zhou, Martin Cmejrek

{"title":"Towards integrated machine translation using structural alignment from syntax-augmented synchronous parsing","authors":"Bing Xiang, Bowen Zhou, Martin Cmejrek","doi":"10.1109/ASRU.2009.5372892","DOIUrl":"https://doi.org/10.1109/ASRU.2009.5372892","url":null,"abstract":"In current statistical machine translation, IBM model based word alignment is widely used as a starting point to build phrase-based machine translation systems. However, such alignment model is separated from the rest of machine translation pipeline and optimized independently. Furthermore, structural information is not taken into account in the alignment model, which sometimes leads to incorrect alignments. In this paper, we present a novel method to connect a re-alignment model with a translation model in an integrated framework. We conduct bilingual chart parsing based on syntax-augmented synchronous context-free grammar. A Viterbi derivation tree is generated for each sentence pair with multiple features employed in a log-linear model. A new word alignment is created under the structural constraint from the Viterbi tree. Extensive experiments are conducted in a Farsi-to-English translation task in conversational speech domain and also a German-to-English translation task in text domain. Systems trained on the new alignment provide significant higher BLEU scores compared to a state-of-the-art baseline.","PeriodicalId":292194,"journal":{"name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132745338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Response timing generation and response type selection for a spontaneous spoken dialog system 自发语音对话系统的响应时间生成和响应类型选择

2009 IEEE Workshop on Automatic Speech Recognition & Understanding Pub Date : 2009-12-01 DOI: 10.1109/ASRU.2009.5372898

Ryota Nishimura, S. Nakagawa

引用次数: 5