2018 IEEE Spoken Language Technology Workshop (SLT)最新文献_第7页

Improving Very Deep Time-Delay Neural Network With Vertical-Attention For Effectively Training CTC-Based ASR Systems 基于垂直注意力的深度时滞神经网络的有效训练

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639675

Sheng Li, Xugang Lu, R. Takashima, Peng Shen, Tatsuya Kawahara, H. Kawai

{"title":"Improving Very Deep Time-Delay Neural Network With Vertical-Attention For Effectively Training CTC-Based ASR Systems","authors":"Sheng Li, Xugang Lu, R. Takashima, Peng Shen, Tatsuya Kawahara, H. Kawai","doi":"10.1109/SLT.2018.8639675","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639675","url":null,"abstract":"The very deep neural network has recently been proposed for speech recognition and achieves significant performance. It has excellent potential for integration with end-to-end (E2E) training. Connectionist temporal classification (CTC) has shown great potential in E2E acoustic modeling. In this study, we investigate deep architectures and techniques which are suitable for CTC-based acoustic modeling. We propose a very deep residual time-delay CTC neural network (VResTD-CTC). How to select a suitable deep architecture optimized with the CTC objective function is crucial for obtaining the state of the art performance. Excellent performances can be obtained by selecting deep architecture for non-E2E ASR systems modeling with tied-triphone states. However, these optimized structures do not guarantee to achieve better or comparable performances on E2E (e.g., CTC-based) systems modeling with dynamic acoustic units. For solving this problem and further leveraging the system performance, we introduce the vertical-attention mechanism to reweight the residual blocks at each time step. Speech recognition experiments show our proposed model significantly outperforms the DNN and LSTM-based (both bidirectional and unidirectional) CTC baseline models.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132009379","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

A Deep Learning Approach for Data Driven Vocal Tract Area Function Estimation 一种数据驱动的声道区域功能估计的深度学习方法

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639582

Sasan Asadiabadi, E. Erzin

引用次数: 3

On-Device End-to-end Speech Recognition with Multi-Step Parallel Rnns 基于多步并行rns的设备端到端语音识别

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639662

Yoonho Boo, Jinhwan Park, Lukas Lee, Wonyong Sung

引用次数: 0

An Experimental Study on Audio Replay Attack Detection Using Deep Neural Networks 基于深度神经网络的音频重放攻击检测实验研究

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639511

Bekir Bakar, C. Hanilçi

{"title":"An Experimental Study on Audio Replay Attack Detection Using Deep Neural Networks","authors":"Bekir Bakar, C. Hanilçi","doi":"10.1109/SLT.2018.8639511","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639511","url":null,"abstract":"Automatic speaker verification (ASV) systems can be easily spoofed by previously recorded speech, synthesized speech and speech signal that artificially generated by voice conversion techniques. In order to increase the reliability of the ASV systems, detecting spoofing attacks whether a given speech signal is genuine or spoofed plays an important role. In this paper, we consider the detection of replay attacks which is the most accessible attack type against ASV systems. To this end, we utilize a deep neural network (DNN) based classifier using features extracted from the long-term average spectrum. The experiments are conducted on the latest edition of Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2017) database. The results are compared with the ASVspoof 2017 baseline system which consists of Gaussian mixture model (GMM) classifier with constant-Q transform cepstral coefficients (CQCC) front-end as well as the GMM with standard mel-frequency cepstrum coefficients (MFCC) features. Experimental results reveal that DNN considerably outperforms the well-known and successful GMM classifier. It is found that long term average spectrum (LTAS) based features are superior to CQCC and MFCC in terms of equal error rate (EER). Finally, we find that high-frequency components convey much more discriminative information for replay attack detection independent of features and classifiers.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115203428","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: 6

Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network 多通道重叠语音识别与位置引导语音提取网络

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639593

Zhuo Chen, Xiong Xiao, Takuya Yoshioka, Hakan Erdogan, Jinyu Li, Y. Gong

{"title":"Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network","authors":"Zhuo Chen, Xiong Xiao, Takuya Yoshioka, Hakan Erdogan, Jinyu Li, Y. Gong","doi":"10.1109/SLT.2018.8639593","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639593","url":null,"abstract":"Although advances in close-talk speech recognition have resulted in relatively low error rates, the recognition performance in far-field environments is still limited due to low signal-to-noise ratio, reverberation, and overlapped speech from simultaneous speakers which is especially more difficult. To solve these problems, beamforming and speech separation networks were previously proposed. However, they tend to suffer from leakage of interfering speech or limited generalizability. In this work, we propose a simple yet effective method for multi-channel far-field overlapped speech recognition. In the proposed system, three different features are formed for each target speaker, namely, spectral, spatial, and angle features. Then a neural network is trained using all features with a target of the clean speech of the required speaker. An iterative update procedure is proposed in which the mask-based beamforming and mask estimation are performed alternatively. The proposed system were evaluated with real recorded meetings with different levels of overlapping ratios. The results show that the proposed system achieves more than 24% relative word error rate (WER) reduction than fixed beamforming with oracle selection. Moreover, as overlap ratio rises from 20% to 70+%, only 3.8% WER increase is observed for the proposed system.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125112513","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: 109

Improving Unsupervised Style Transfer in end-to-end Speech Synthesis with end-to-end Speech Recognition 用端到端语音识别改进端到端语音合成中的无监督风格迁移

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639672

Da-Rong Liu, Chi-Yu Yang, Szu-Lin Wu, Hung-yi Lee

引用次数: 17

MOS Naturalness and the Quest for Human-Like Speech MOS的自然性和对类人语言的探索

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639599

S. Shirali-Shahreza, Gerald Penn

引用次数: 12

Speaker Adaptation for End-to-End CTC Models 端到端CTC模型的说话人自适应

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639644

Ke Li, Jinyu Li, Yong Zhao, Kshitiz Kumar, Y. Gong

引用次数: 20

A Spectrally Weighted Mixture of Least Square Error and Wasserstein Discriminator Loss for Generative SPSS 生成式SPSS中最小二乘误差和Wasserstein判别器损失的谱加权混合

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639609

G. Degottex, M. Gales

引用次数: 1

Discourse Modeling of Non-Native Spontaneous Speech Using the Rhetorical Structure Theory Framework 基于修辞结构理论框架的非母语自发语篇建模

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639509

Xinhao Wang, Binod Gyawali, James V. Bruno, Hillary R. Molloy, Keelan Evanini, K. Zechner

{"title":"Discourse Modeling of Non-Native Spontaneous Speech Using the Rhetorical Structure Theory Framework","authors":"Xinhao Wang, Binod Gyawali, James V. Bruno, Hillary R. Molloy, Keelan Evanini, K. Zechner","doi":"10.1109/SLT.2018.8639509","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639509","url":null,"abstract":"This study aims to model the discourse structure of spontaneous spoken responses within the context of an assessment of English speaking proficiency for non-native speakers. Rhetorical Structure Theory (RST) has been commonly used in the analysis of discourse organization of written texts; however, limited research has been conducted to date on RST annotation and parsing of spoken language, in particular, non-native spontaneous speech. Due to the fact that the measurement of discourse coherence is typically a key metric in human scoring rubrics for assessments of spoken language, we initiated a research to first obtain RST annotations on non-native spoken responses from a standardized assessment of academic English proficiency. Afterwards, based on the annotations obtained, automatic parsers were built to process non-native spontaneous speech. Finally, a set of effective features were extracted from both manually annotated and automatically generated RST trees to evaluate the discourse structure of non-native spontaneous speech, and then employed to further improve the validity of an automated speech scoring system.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127910812","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