2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)最新文献

Global F0 control parameter prediction based on impressions for communicative prosody generation 基于印象的交流韵律生成的全局F0控制参数预测

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-12-01 DOI: 10.1109/ICSDA.2013.6709871

L. Shao, Y. Greenberg, Y. Sagisaka

引用次数: 7

Blind source separation: A review and analysis 盲源分离:综述与分析

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709849

Madhab Pal, Rajib Roy, Joyanta Basu, M. S. Bepari

引用次数: 45

An evaluation of Mongolian data-driven Text-to-Speech 蒙古语数据驱动文本转语音的评价

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709881

Altangerel Chagnaa, Purev Jaimai, Kerey Yesyenbyek, C. Hansakunbuntheung

引用次数: 0

Improve Japanese C2L learners' capability to distinguish Chinese tone 2 and tone 3 through perceptual training 通过感知训练提高日语C2L学习者区分汉语二、三声调的能力

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709850

Jinsong Zhang, Xiaoyun Wang, Yue Sun, M. Nishida, T. Zou, Seiichi Yamamoto

{"title":"Improve Japanese C2L learners' capability to distinguish Chinese tone 2 and tone 3 through perceptual training","authors":"Jinsong Zhang, Xiaoyun Wang, Yue Sun, M. Nishida, T. Zou, Seiichi Yamamoto","doi":"10.1109/ICSDA.2013.6709850","DOIUrl":"https://doi.org/10.1109/ICSDA.2013.6709850","url":null,"abstract":"In the process of Chinese learning, Tone 2 and Tone 3 are the most problematic pair for Japanese learners. We propose to develop a perceptual training paradigm to help them to gain efficiently the perceptual ability to distinguish the tones. A series of three studies were carried out: the first checked how difficult the Japanese learners produce the tones. The second investigated how differently Japanese and Chinese people perceive the two tones. The third tested a hybrid perceptual training paradigm lasting 6 days: a 2-days-long adaptive training followed by a 4-days-long high-variability training. Results of these studies not only improved our knowledge about tone production and perception patterns with respect to Japanese and Chinese speakers, but also showed the effectiveness of the proposed hybrid perceptual training paradigm which achieved a significant improvement of tone distinguishing ability (a relative error reduction of 77% in 6 days) by 6 Japanese participants.","PeriodicalId":266295,"journal":{"name":"2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122866946","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: 4

A syllable-based framework for unit selection synthesis in 13 Indian languages 13种印度语言中基于音节的单位选择合成框架

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709851

H. Patil, T. Patel, Nirmesh J. Shah, Hardik B. Sailor, R. Krishnan, G. Kasthuri, T. Nagarajan, S. Christina, Naresh Kumar, Veera Raghavendra, K. Prahallad, S. Prasanna, Nagaraj Adiga, Sanasam Ranbir Singh, Anand Konjengbam, Pranaw Kumar, Bira Chandra Singh, S. Kumar, T. G. Bhadran, T. Sajini, Arup Saha, T. Basu, K. S. Rao, N. Narendra, A. Sao, Rakesh Kumar, P. Talukdar, P. Acharyaa, S. Chandra, Swaran Lata, H. Murthy

{"title":"A syllable-based framework for unit selection synthesis in 13 Indian languages","authors":"H. Patil, T. Patel, Nirmesh J. Shah, Hardik B. Sailor, R. Krishnan, G. Kasthuri, T. Nagarajan, S. Christina, Naresh Kumar, Veera Raghavendra, K. Prahallad, S. Prasanna, Nagaraj Adiga, Sanasam Ranbir Singh, Anand Konjengbam, Pranaw Kumar, Bira Chandra Singh, S. Kumar, T. G. Bhadran, T. Sajini, Arup Saha, T. Basu, K. S. Rao, N. Narendra, A. Sao, Rakesh Kumar, P. Talukdar, P. Acharyaa, S. Chandra, Swaran Lata, H. Murthy","doi":"10.1109/ICSDA.2013.6709851","DOIUrl":"https://doi.org/10.1109/ICSDA.2013.6709851","url":null,"abstract":"In this paper, we discuss a consortium effort on building text to speech (TTS) systems for 13 Indian languages. There are about 1652 Indian languages. A unified framework is therefore attempted required for building TTSes for Indian languages. As Indian languages are syllable-timed, a syllable-based framework is developed. As quality of speech synthesis is of paramount interest, unit-selection synthesizers are built. Building TTS systems for low-resource languages requires that the data be carefully collected an annotated as the database has to be built from the scratch. Various criteria have to addressed while building the database, namely, speaker selection, pronunciation variation, optimal text selection, handling of out of vocabulary words and so on. The various characteristics of the voice that affect speech synthesis quality are first analysed. Next the design of the corpus of each of the Indian languages is tabulated. The collected data is labeled at the syllable level using a semiautomatic labeling tool. Text to speech synthesizers are built for all the 13 languages, namely, Hindi, Tamil, Marathi, Bengali, Malayalam, Telugu, Kannada, Gujarati, Rajasthani, Assamese, Manipuri, Odia and Bodo using the same common framework. The TTS systems are evaluated using degradation Mean Opinion Score (DMOS) and Word Error Rate (WER). An average DMOS score of ≈3.0 and an average WER of about 20 % is observed across all the languages.","PeriodicalId":266295,"journal":{"name":"2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129449707","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: 58

Development of a standard text and speech corpus for the Punjabi language 开发旁遮普语的标准文本和语音语料库

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709891

S. Dhanjal, S. S. Bhatia

引用次数: 6

Evaluation and error recovery methods of an IVR based real time speech recognition application 基于IVR的实时语音识别应用的评估和错误恢复方法

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709847

Soma Khan, Joyanta Basu, M. S. Bepari, Rajib Roy

{"title":"Evaluation and error recovery methods of an IVR based real time speech recognition application","authors":"Soma Khan, Joyanta Basu, M. S. Bepari, Rajib Roy","doi":"10.1109/ICSDA.2013.6709847","DOIUrl":"https://doi.org/10.1109/ICSDA.2013.6709847","url":null,"abstract":"Field trial and evaluation of any real world speech recognition application using Interactive Voice Response technology are likely to be a daunting task. It has to face challenges regarding spoken language conventions, pronunciation variations, recognition issues in noisy environment, limitations of human cognition, working memory and differences between users. Present study illustrates the entire evaluation process of such an agricultural information retrieval system mainly targeted towards semi-literate or illiterate farmers. A new set of evaluation metrics as per the designed evaluation strategies, details of field trial processes, feedback analysis and finally system performance results are presented in a well organized way. Additionally to meet users' expectations, distinctive error recovery methods like Signal Analysis and Decision, Confidence Measure and Polling, Complementary Information, Runtime model generation etc. are introduced and incorporated to confirm performance enhancement in final trial. Evaluation methods and metrics used here are domain independent and applicable to similar systems.","PeriodicalId":266295,"journal":{"name":"2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115836126","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: 3

PL-ILT: A web tool for creation of pronunciation lexicon in Indian languages 一个用于创建印度语言发音词典的网络工具

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709858

Sankar Mukherjee, S. Mandal

引用次数: 0

Evaluation of prosody in text-to-speech synthesis system of Bangla 孟加拉语文本-语音合成系统的韵律评价

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709868

T. Basu, Arup Saha

引用次数: 2

Multi-speaker, narrowband, continuous Marathi speech database 多扬声器，窄带，连续马拉地语语音数据库

2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) Pub Date : 2013-11-01 DOI: 10.1109/ICSDA.2013.6709844

Tejas Godambe, N. Bondale, K. Samudravijaya, P. Rao

引用次数: 6