2019 National Conference on Communications (NCC)最新文献_第7页

Comparison of low-dimension speech segment embeddings: Application to speaker diarization 低维语音片段嵌入的比较:在说话人拨号化中的应用

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732210

Srikanth Raj Chetupalli, T. Sreenivas, Anand Gopalakrishnan

引用次数: 0

Speaking-Rate Adaptation of Automatic Speech Recognition System through Fuzzy Classification based Time-Scale Modification 基于模糊分类时标修正的语音自动识别系统语速自适应

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732255

S. Shahnawazuddin, Waquar Ahmad, H. Kathania, Nagaraj Adiga, B. Sai

{"title":"Speaking-Rate Adaptation of Automatic Speech Recognition System through Fuzzy Classification based Time-Scale Modification","authors":"S. Shahnawazuddin, Waquar Ahmad, H. Kathania, Nagaraj Adiga, B. Sai","doi":"10.1109/NCC.2019.8732255","DOIUrl":"https://doi.org/10.1109/NCC.2019.8732255","url":null,"abstract":"In this paper, we study the role of speaking-rate adaptation (SRA) of automatic speech recognition (ASR) systems. The performance of an ASR system is reported to degrade when the speaking-rate is either too fast or too slow. In order to simulate such a situation, an ASR system was trained on adults' speech and used for transcribing speech data from adult as well as child speakers. Earlier studies have shown that, speaking-rate is significantly lower in the case of children when compared to adults. Consequently, the recognition performance for children's speech was noted to be very poor in contrast to adults' speech. To improve the recognition performance with respect to children's speech, speaking-rate was explicitly changed using time-scale modification (TSM). A recently proposed TSM approach based on fuzzy classification of spectral bins has been explored in this regard. The fuzzy-classification-based TSM technique is reported to be superior to state-of-the-art approaches. Effectiveness of the said TSM technique has not been studied yet in the context of ASR. The experimental studies presented in this paper show that SRA based on fuzzy classification results in a relative improvement of 30% over the baseline.","PeriodicalId":6870,"journal":{"name":"2019 National Conference on Communications (NCC)","volume":"18 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90581015","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

Caching Partial Files for Content Delivery 为内容交付缓存部分文件

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732266

V. S. C. L. Narayana, Sambhav Jain, Sharayu Moharir

引用次数: 2

Decision Support System for Liver Cancer Diagnosis using Focus Features in NSCT Domain 基于NSCT域焦点特征的肝癌诊断决策支持系统

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732219

Lakshmipriya Balagourouchetty, Jayanthi K. Pragatheeswaran, B. Pottakkat, R. Govindarajalou

引用次数: 1

Detection of Vowel-Like Speech Using Variance of Sample Magnitudes 基于样本幅度方差的类元音语音检测

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732268

N. Srinivas, G. Pradhan, P. Kumar

引用次数: 0

SSK Performance with SWIPT based Dual-Hop AF Relay over Rayleigh Fading 基于SWIPT的瑞利衰落双跳AF中继的SSK性能

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732187

H. Sahu, P. R. Sahu

引用次数: 1

Modelling and short term forecasting of flash floods in an urban environment 城市环境下山洪暴发的建模与短期预报

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732193

Suraj Ogale, S. Srivastava

引用次数: 4

The HTTP/2 Server Push and Its Implications on Mobile Web Quality of Experience HTTP/2服务器推送及其对移动Web体验质量的影响

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732204

Hema Kumar Yarnagula, V. Tamarapalli

{"title":"The HTTP/2 Server Push and Its Implications on Mobile Web Quality of Experience","authors":"Hema Kumar Yarnagula, V. Tamarapalli","doi":"10.1109/NCC.2019.8732204","DOIUrl":"https://doi.org/10.1109/NCC.2019.8732204","url":null,"abstract":"In recent years, an unprecedented growth in the usage of mobile devices for web browsing poses a challenge for the service providers to assure the user-perceived quality. In the context of web quality of experience (QoE), quality perception is mostly dominated by the page load time (PLT). HTTP/2 protocol, with the server push feature, promises to address the design limitations of HTTP/1.1 that inhibit optimal web performance. However, it remains largely unclear if HTTP/2 can really improve web QoE for mobile browsing. In this paper, we experimentally investigate the web QoE with HTTP/2. We assess the web QoE for several popular websites on a controlled testbed emulated with real 4G/LTE and 3G network traces. Our experiments investigate the impact of both network latency and packet loss ratio on the mobile web QoE. The results clearly show 24% improvement in the PLT, on an average, with HTTP/2 over mobile networks. However, we identify that HTTP/2 with server push is necessarily not the fail-safe solution for improving mobile web QoE under all conditions. We noticed that HTTP/2 loads the web pages slower than HTTP/1.1 when the network packet loss ratio is more than 2%. Our study could be used as the basis to derive a set of guidelines on the usage of the HTTP/2 server push to improve the end-user web QoE, especially in mobile devices.","PeriodicalId":6870,"journal":{"name":"2019 National Conference on Communications (NCC)","volume":"104 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87594444","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: 1

Detection of Vowels in Speech Signals Degraded by Speech-Like Noise 类语音噪声退化语音信号中元音的检测

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732212

Avinash Kumar, S. Shahnawazuddin, Sarmila Garnaik, Ishwar Chandra Yadav, G. Pradhan

{"title":"Detection of Vowels in Speech Signals Degraded by Speech-Like Noise","authors":"Avinash Kumar, S. Shahnawazuddin, Sarmila Garnaik, Ishwar Chandra Yadav, G. Pradhan","doi":"10.1109/NCC.2019.8732212","DOIUrl":"https://doi.org/10.1109/NCC.2019.8732212","url":null,"abstract":"Detecting vowels in a noisy speech signal is a very challenging task. The problem is further aggravated when the noise exhibits speech-like characteristics, e.g., babble noise. In this work, a novel front-end feature extraction technique exploiting variational mode decomposition (VMD) is proposed to improve the detection of vowels in speech data degraded by speech-like noise. Each short-time analysis frame of speech is first decomposed into a set of variational mode functions (VMFs) using VMD. The logarithmic energy present in each of the VMFs is then used as the front-end features for detecting vowels. A three-class classifier (vowel, non-vowel and silence) with acoustic modeling based on long short-term memory (LSTM) architecture is developed on the TIMIT database using the proposed features as well as mel-frequency cepstral coefficients (MFCC). Using the three-class classifier, frame-level time-alignments for a given speech utterance are obtained to detect the vowel regions. The proposed features result in significantly improved performance under noisy test conditions than the MFCC features. Further, the vowel regions detected using the proposed features are also quite different from those obtained through the MFCC. Exploiting the aforementioned differences, the evidences are combined to further improve the detection accuracy.","PeriodicalId":6870,"journal":{"name":"2019 National Conference on Communications (NCC)","volume":"66 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83927498","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

General Compute and Forward for Virtual Full-Duplex Relaying 虚拟全双工中继的通用计算和转发

2019 National Conference on Communications (NCC) Pub Date : 2019-02-01 DOI: 10.1109/NCC.2019.8732252

Roshan S. Sam, Antony V. Mampilly, S. Bhashyam

引用次数: 0