2018 IEEE Spoken Language Technology Workshop (SLT)最新文献_第2页

Data Selection for Improving Naturalness of TTS Voices Trained on Small Found Corpuses 提高小语料库TTS语音训练自然度的数据选择

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639642

Fang-Yu Kuo, S. Aryal, G. Degottex, S. Kang, P. Lanchantin, I. Ouyang

引用次数: 10

Generating Semantic Similarity Atlas for Natural Languages 自然语言语义相似图谱的生成

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/slt.2018.8639521

Lutfi Kerem Senel, Ihsan Utlu, Veysel Yücesoy, Aykut Koç, T. Çukur

引用次数: 7

Dynamic Extension of ASR Lexicon Using Wikipedia Data 使用维基百科数据的ASR词典动态扩展

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639592

Badr M. Abdullah, I. Illina, D. Fohr

引用次数: 0

Convolutional Neural Networks for Dialogue State Tracking without Pre-Trained Word Vectors or Semantic Dictionaries 无预训练词向量或语义字典的对话状态跟踪卷积神经网络

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639559

M. Korpusik, James R. Glass

{"title":"Convolutional Neural Networks for Dialogue State Tracking without Pre-Trained Word Vectors or Semantic Dictionaries","authors":"M. Korpusik, James R. Glass","doi":"10.1109/SLT.2018.8639559","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639559","url":null,"abstract":"A crucial step in task-oriented dialogue systems is tracking the user’s goal over the course of the conversation. This involves maintaining a probability distribution over possible values for each slot (e.g., the foodslot might map to the value Turkish), which gets updated at each turn of the dialogue. Previously, rule-based methods were applied to dialogue systems, or models that required hand-crafted semantic dictionaries mapping phrases to those that are similar in meaning (e.g., areamight map to part of town). However, these are expensive to design for each domain, limiting the generalizability. In addition, often a spoken language understanding (SLU) component precedes the dialogue state update mechanism; however, this leads to compounded errors as the output from one module is passed to the next. Instead, more recent work has explored deep learning models for directly updating dialogue state, bypassing the need for SLU or expert-engineered rules. We demonstrate that a novel convolutional neural architecture without any pre-trained word vectors or semantic dictionaries achieves 86.9% joint goal accuracy and 95.4% requested slot accuracy on WOZ 2.0.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"141 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":"132833581","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: 7

Occam’s Adaptation: A Comparison of Interpolation of Bases Adaptation Methods for Multi-Dialect Acoustic Modeling with LSTMS Occam的自适应:基于LSTMS的多方言声学建模的基数自适应插值方法比较

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639654

M. Grace, M. Bastani, Eugene Weinstein

{"title":"Occam’s Adaptation: A Comparison of Interpolation of Bases Adaptation Methods for Multi-Dialect Acoustic Modeling with LSTMS","authors":"M. Grace, M. Bastani, Eugene Weinstein","doi":"10.1109/SLT.2018.8639654","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639654","url":null,"abstract":"Multidialectal languages can pose challenges for acoustic modeling. Past research has shown that with a large training corpus but without explicit modeling of inter-dialect variability, training individual per-dialect models yields superior performance to that of a single model trained on the combined data [1, 2]. In this work, we were motivated by the idea that adaptation techniques can allow the models to learn dialect-independent features and in turn leverage the power of the larger training corpus sizes afforded when pooling data across dialects. Our goal was thus to create a single multidialect acoustic model that would rival the performance of the dialect-specific models.Working in the context of deep Long-Short Term Memory (LSTM) acoustic models trained on up to 40K hours of speech, we explored several methods for training and incorporating dialect-specific information into the model, including 12 variants of interpolation-of-bases techniques related to Cluster Adaptive Training (CAT) [3] and Factorized Hidden Layer (FHL) [4] techniques. We found that with our model topology and large training corpus, simply appending the dialect-specific information to the feature vector resulted in a more accurate model than any of the more complex interpolation-of-bases techniques, while requiring less model complexity and fewer parameters. This simple adaptation yielded a single unified model for all dialects that, in most cases, outperformed individual models which had been trained per-dialect.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"16 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":"123102181","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: 14

Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding 口语理解中域、意图和槽的耦合表示学习

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639581

Jihwan Lee, Dongchan Kim, R. Sarikaya, Young-Bum Kim

引用次数: 11

Multi-Objective Multi-Task Learning on RNNLM for Speech Recognition 基于RNNLM的多目标多任务学习语音识别

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639649

Minguang Song, Yunxin Zhao, Shaojun Wang

{"title":"Multi-Objective Multi-Task Learning on RNNLM for Speech Recognition","authors":"Minguang Song, Yunxin Zhao, Shaojun Wang","doi":"10.1109/SLT.2018.8639649","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639649","url":null,"abstract":"The cross entropy (CE) loss function is commonly adopted for neural network language model (NNLM) training. Although this criterion is largely successful, as evidenced by the quick advance of NNLM, minimizing CE only maximizes likelihood of training data. When training data is insufficient, the generalization power of the resulting LM is limited on test data. In this paper, we propose to integrate a pairwise ranking (PR) loss with the CE loss for multi-objective training on recurrent neural network language model (RNNLM). The PR loss emphasizes discrimination between target and non-target words and also reserves probabilities for low-frequency correct words, which complements the distribution learning role of the CE loss. Combining the two losses may therefore help improve the performance of RNNLM. In addition, we incorporate multi-task learning (MTL) into the proposed multi-objective learning to regularize the primary task of RNNLM by an auxiliary task of part-of-speech (POS) tagging. The proposed approach to RNNLM learning has been evaluated on two speech recognition tasks of WSJ and AMI with encouraging results achieved on word error rate reductions.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"14 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":"121044007","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

Parameter Generation Algorithms for Text-To-Speech Synthesis with Recurrent Neural Networks 基于递归神经网络的文本-语音合成参数生成算法

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639626

V. Klimkov, A. Moinet, Adam Nadolski, Thomas Drugman

引用次数: 5

Short Utterance Speaker Recognition by Reservoir with Self-Organized Mapping 基于自组织映射的库识别短话语说话人

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639570

Narumitsu Ikeda, Yoshinao Sato, Hirokazu Takahashi

{"title":"Short Utterance Speaker Recognition by Reservoir with Self-Organized Mapping","authors":"Narumitsu Ikeda, Yoshinao Sato, Hirokazu Takahashi","doi":"10.1109/SLT.2018.8639570","DOIUrl":"https://doi.org/10.1109/SLT.2018.8639570","url":null,"abstract":"Short utterances cause performance degradation in conventional speaker recognition systems based on i-vector, which relies on the statistics of spectral features. To overcome this difficulty, we propose a novel method that utilizes the dynamics of the spectral features as well as their distribution. Our model integrates echo state network (ESN), a type of reservoir computing architecture, and self-organizing map (SOM), a competitive learning network. The ESN consists of a single-hidden-layer recurrent neural network with randomly fixed weights, which extracts temporal patterns of the spectral features. The input weights of our model are trained using the unsupervised competitive learning algorithm of the SOM, before enrollment, to extract the intrinsic structure of the spectral features, whereas the input weights are fixed randomly in the original ESN. In enrollment, the output weights are trained in a supervised manner to recognize an individual in a group of speakers. Our experiment demonstrates that the proposed method outperforms or is comparable to a baseline i-vector system for text-independent speaker identification on short utterances.","PeriodicalId":377307,"journal":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"31 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":"128098956","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

Examplar-Based Speechwaveform Generation for Text-To-Speech 文本到语音的基于示例的语音波形生成

2018 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2018-12-01 DOI: 10.1109/SLT.2018.8639679

Cassia Valentini-Botinhao, O. Watts, Felipe Espic, Simon King

引用次数: 0