2018 IEEE Spoken Language Technology Workshop (SLT)最新文献_第5页

Evaluating on-device ASR on Field Recordings from an Interactive Reading Companion 评估交互式阅读伴侣现场记录的设备上ASR

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639603

Anastassia Loukina, Nitin Madnani, Beata Beigman Klebanov, A. Misra, Georgi Angelov, O. Todic

引用次数: 4

An Icelandic Pronunciation Dictionary for TTS 冰岛语TTS发音字典

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639590

Anna Björk Nikulásdóttir, Jón Guðnason, Eiríkur Rögnvaldsson

引用次数: 10

Toward Multi-Features Emphasis Speech Translation: Assessment of Human Emphasis Production and Perception with Speech and Text Clues 走向多特征重音翻译:基于语音和文本线索的人类重音产生和感知评价

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639641

Quoc Truong Do, S. Sakti, Satoshi Nakamura

{"title":"Toward Multi-Features Emphasis Speech Translation: Assessment of Human Emphasis Production and Perception with Speech and Text Clues","authors":"Quoc Truong Do, S. Sakti, Satoshi Nakamura","doi":"10.1109/SLT.2018.8639641","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639641","url":null,"abstract":"Emphasis is an important factor of human speech that helps convey emotion and the focused information of utterances. Recently, studies have been conducted on speech-to-speech translation to preserve the emphasis information from the source language to the target language. However, since different cultures have various ways of expressing emphasis, just considering the acoustic-to-acoustic feature emphasis translation may not always reflect the experiences of users. On the other hand, emphasis can be expressed at various levels in both text and speech. However, it remains unclear how we communicate emphasis in a different form (acoustic/linguistic) with different levels and whether we can perceive the difference between different levels of emphasis or observe the similarity of the same emphasis levels in both text and speech forms. In this paper, we conducted analyses on human perception of emphasis with both speech and text clues through crowd-sourced evaluations. The results indicate that although participants can distinguish among emphasis levels and perceive the same emphasis level between speech and text, many ambiguities still exist at certain emphasis levels. Thus, our result provides insight into what needs to be handled during the emphasis translation process.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 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":"117163567","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: 2

An Evaluation of Deep Spectral Mappings and WaveNet Vocoder for Voice Conversion 语音转换中深度光谱映射和波网声码器的评价

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639608

Patrick Lumban Tobing, Tomoki Hayashi, Yi-Chiao Wu, Kazuhiro Kobayashi, T. Toda

{"title":"An Evaluation of Deep Spectral Mappings and WaveNet Vocoder for Voice Conversion","authors":"Patrick Lumban Tobing, Tomoki Hayashi, Yi-Chiao Wu, Kazuhiro Kobayashi, T. Toda","doi":"10.1109/SLT.2018.8639608","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639608","url":null,"abstract":"This paper presents an evaluation of deep spectral mapping and WaveNet vocoder in voice conversion (VC). In our VC framework, spectral features of an input speaker are converted into those of a target speaker using the deep spectral mapping, and then together with the excitation features, the converted waveform is generated using WaveNet vocoder. In this work, we compare three different deep spectral mapping networks, i.e., a deep single density network (DSDN), a deep mixture density network (DMDN), and a long short-term memory recurrent neural network with an autoregressive output layer (LSTM-AR). Moreover, we also investigate several methods for reducing mismatches of spectral features used in WaveNet vocoder between training and conversion processes, such as some methods to alleviate oversmoothing effects of the converted spectral features, and another method to refine WaveNet using the converted spectral features. The experimental results demonstrate that the LSTM-AR yields nearly better spectral mapping accuracy than the others, and the proposed WaveNet refinement method significantly improves the naturalness of the converted waveform.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"35 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":"117266383","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: 10

High-Degree Feature for Deep Neural Network Based Acoustic Model 基于深度神经网络的声学模型的高阶特征

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639524

Hoon Chung, Sung Joo Lee, J. Park

引用次数: 0

Multichannel ASR with Knowledge Distillation and Generalized Cross Correlation Feature 基于知识蒸馏和广义互相关特征的多通道ASR

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639600

Wenjie Li, Yu Zhang, Pengyuan Zhang, Fengpei Ge

引用次数: 2

A K-Nearest Neighbours Approach To Unsupervised Spoken Term Discovery 无监督口语词汇发现的k近邻方法

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639515

Alexis Thual, Corentin Dancette, Julien Karadayi, Juan Benjumea, Emmanuel Dupoux

引用次数: 11

Improved Auto-Marking Confidence for Spoken Language Assessment 提高了口语评估的自动评分信心

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639634

Marco Del Vecchio, A. Malinin, M. Gales

{"title":"Improved Auto-Marking Confidence for Spoken Language Assessment","authors":"Marco Del Vecchio, A. Malinin, M. Gales","doi":"10.1109/SLT.2018.8639634","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639634","url":null,"abstract":"Automatic assessment of spoken language proficiency is a sought-after technology. These systems often need to handle the operating scenario where candidates have a skill level or first language which was not encountered during the training stage. For high stakes tests it is necessary for those systems to have good grading performance when the candidate is from the same population as those contained in the training set, and they should know when they are likely to perform badly in the case when the candidate is not from the same population as the ones contained in training set. This paper focuses on using Deep Density Networks to yield auto-marking confidence. Firstly, we explore the benefits of parametrising either a predictive distribution or a posterior distribution over the parameters of the model likelihood and obtaining the predictive distribution via marginalisation. Secondly, we investigate how it is possible to act on the parametrised density in order to explicitly teach the model to have low confidence in areas of the observation space where there is no training data by assigning confidence scores to artificially generated data. Lastly, we compare the capabilities of Factor Analysis, Variational Auto-Encodes, and Wasserstein Generative Adversarial Networks to generate artificial data.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"21 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":"124020335","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: 2

Hierarchical RNNs for Waveform-Level Speech Synthesis 用于波形级语音合成的分层rnn

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639588

Qingyun Dou, Moquan Wan, G. Degottex, Zhiyi Ma, M. Gales

{"title":"Hierarchical RNNs for Waveform-Level Speech Synthesis","authors":"Qingyun Dou, Moquan Wan, G. Degottex, Zhiyi Ma, M. Gales","doi":"10.1109/SLT.2018.8639588","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639588","url":null,"abstract":"Speech synthesis technology has a wide range of applications such as voice assistants. In recent years waveform-level synthesis systems have achieved state-of-the-art performance, as they overcome the limitations of vocoder-based synthesis systems. A range of waveform-level synthesis systems have been proposed; this paper investigates the performance of hierarchical Recurrent Neural Networks (RNNs) for speech synthesis. First, the form of network conditioning is discussed, comparing linguistic features and vocoder features from a vocoder-based synthesis system. It is found that compared with linguistic features, conditioning on vocoder features requires less data and modeling power, and yields better performance when there is limited data. By conditioning the hierarchical RNN on vocoder features, this paper develops a neural vocoder, which is capable of high quality synthesis when there is sufficient data. Furthermore, this neural vocoder is flexible, as conceptually it can map any sequence of vocoder features to speech, enabling efficient synthesizer porting to a target speaker. Subjective listening tests demonstrate that the neural vocoder outperforms a high quality baseline, and that it can change its voice to a very different speaker, given less than 15 minutes of data for fine tuning.","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":"116810829","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: 2

LSTM Language Model Adaptation with Images and Titles for Multimedia Automatic Speech Recognition 基于图像和标题的LSTM语言模型自适应多媒体自动语音识别

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639551

Yasufumi Moriya, G. Jones

引用次数: 14