2021 IEEE Spoken Language Technology Workshop (SLT)最新文献_第4页

Getting Your Conversation on Track: Estimation of Residual Life for Conversations 让你的谈话走上正轨:对谈话剩余寿命的估计

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383544

Zexin Lu, Jing Li, Yingyi Zhang, Haisong Zhang

引用次数: 0

Large-Context Conversational Representation Learning: Self-Supervised Learning For Conversational Documents 大语境会话表示学习:会话文档的自监督学习

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383584

Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi

{"title":"Large-Context Conversational Representation Learning: Self-Supervised Learning For Conversational Documents","authors":"Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi","doi":"10.1109/SLT48900.2021.9383584","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383584","url":null,"abstract":"This paper presents a novel self-supervised learning method for handling conversational documents consisting of transcribed text of human-to-human conversations. One of the key technologies for understanding conversational documents is utterance-level sequential labeling, where labels are estimated from the documents in an utterance-by-utterance manner. The main issue with utterance-level sequential labeling is the difficulty of collecting labeled conversational documents, as manual annotations are very costly. To deal with this issue, we propose large-context conversational representation learning (LC-CRL), a self-supervised learning method specialized for conversational documents. A self-supervised learning task in LC-CRL involves the estimation of an utterance using all the surrounding utterances based on large-context language modeling. In this way, LC-CRL enables us to effectively utilize unlabeled conversational documents and thereby enhances the utterance-level sequential labeling. The results of experiments on scene segmentation tasks using contact center conversational datasets demonstrate the effectiveness of the proposed method.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133875541","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

Improved Parallel Wavegan Vocoder with Perceptually Weighted Spectrogram Loss 基于感知加权谱图损失的改进并行波形声码器

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383549

Eunwoo Song, Ryuichi Yamamoto, Min-Jae Hwang, Jin-Seob Kim, Ohsung Kwon, Jae-Min Kim

引用次数: 14

Articulatory Comparison of L1 and L2 Speech for Mispronunciation Diagnosis 母语和第二语言发音对比诊断错误发音

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383574

Subash Khanal, Michael T. Johnson, Narjes Bozorg

引用次数: 5

Efficient Large Scale Semi-Supervised Learning for CTC Based Acoustic Models 基于CTC的声学模型的高效大规模半监督学习

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383536

Prakhar Swarup, D. Chakrabarty, A. Sapru, Hitesh Tulsiani, Harish Arsikere, S. Garimella

引用次数: 1

An Exploration of Log-Mel Spectrogram and MFCC Features for Alzheimer’s Dementia Recognition from Spontaneous Speech 基于Log-Mel谱图和MFCC特征的自发性言语识别阿尔茨海默氏痴呆症的研究

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383491

Amit Meghanani, S. AnoopC., A. Ramakrishnan

引用次数: 45

Personalized Extractive Summarization for a News Dialogue System 面向新闻对话系统的个性化抽取摘要

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383568

Hiroaki Takatsu, Mayu Okuda, Yoichi Matsuyama, Hiroshi Honda, S. Fujie, Tetsunori Kobayashi

{"title":"Personalized Extractive Summarization for a News Dialogue System","authors":"Hiroaki Takatsu, Mayu Okuda, Yoichi Matsuyama, Hiroshi Honda, S. Fujie, Tetsunori Kobayashi","doi":"10.1109/SLT48900.2021.9383568","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383568","url":null,"abstract":"In modern society, people’s interests and preferences are diversifying. Along with this, the demand for personalized summarization technology is increasing. In this study, we propose a method for generating summaries tailored to each user’s interests using profile features obtained from questionnaires administered to users of our spoken-dialogue news delivery system. We propose a method that collects and uses the obtained user profile features to generate a summary tailored to each user’s interests, specifically, the sentence features obtained by BERT and user profile features obtained from the questionnaire result. In addition, we propose a method for extracting sentences by solving an integer linear programming problem that considers redundancy and context coherence, using the degree of interest in sentences estimated by the model. The results of our experiments confirmed that summaries generated based on the degree of interest in sentences estimated using user profile information can transmit information more efficiently than summaries based solely on the importance of sentences.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115879224","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

Transformer-Based Direct Speech-To-Speech Translation with Transcoder 基于转换器的直接语音到语音翻译

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383496

Takatomo Kano, S. Sakti, Satoshi Nakamura

{"title":"Transformer-Based Direct Speech-To-Speech Translation with Transcoder","authors":"Takatomo Kano, S. Sakti, Satoshi Nakamura","doi":"10.1109/SLT48900.2021.9383496","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383496","url":null,"abstract":"Traditional speech translation systems use a cascade manner that concatenates speech recognition (ASR), machine translation (MT), and text-to-speech (TTS) synthesis to translate speech from one language to another language in a step-by-step manner. Unfortunately, since those components are trained separately, MT often struggles to handle ASR errors, resulting in unnatural translation results. Recently, one work attempted to construct direct speech translation in a single model. The model used a multi-task scheme that learns to predict not only the target speech spectrograms directly but also the source and target phoneme transcription as auxiliary tasks. However, that work was only evaluated Spanish-English language pairs with similar syntax and word order. With syntactically distant language pairs, speech translation requires distant word order, and thus direct speech frame-to-frame alignments become difficult. Another direction was to construct a single deep-learning framework while keeping the step-by-step translation process. However, such studies focused only on speech-to-text translation. Furthermore, all of these works were based on a recurrent neural net-work (RNN) model. In this work, we propose a step-by-step scheme to a complete end-to-end speech-to-speech translation and propose a Transformer-based speech translation using Transcoder. We compare our proposed and multi-task model using syntactically similar and distant language pairs.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130703512","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: 33

Through the Words of Viewers: Using Comment-Content Entangled Network for Humor Impression Recognition 通过观众的话语:利用评论-内容纠缠网络进行幽默印象识别

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383564

Huan-Yu Chen, Yun-Shao Lin, Chi-Chun Lee

{"title":"Through the Words of Viewers: Using Comment-Content Entangled Network for Humor Impression Recognition","authors":"Huan-Yu Chen, Yun-Shao Lin, Chi-Chun Lee","doi":"10.1109/SLT48900.2021.9383564","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383564","url":null,"abstract":"Research into understanding humor has been investigated over centuries. It has recently attracted various technical effort in computing humor automatically from data, especially for humor in speech. Comprehension on the same speech and the ability to realize a humor event vary depending on each individual audience’s background and experience. Most previous works on automatic humor detection or impression recognition mainly model the produced textual content only without considering audience responses. We collect a corpus of TED Talks including audience comments for each of the presented TED speech. We propose a novel network architecture that considers the natural entanglement between speech transcripts and user’s online feedbacks as an integrative graph structure, where the content speech and online feedbacks are nodes where the edges are connected though their common words. Our model achieves 61.2% of accuracy in a three-class classification on humor impression recognition on TED talks; our experiments further demonstrate viewers comments are essential in improving the recognition tasks, and a joint content-comment modeling achieves the best recognition.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"19 5part1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113963900","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

Analysis of Multimodal Features for Speaking Proficiency Scoring in an Interview Dialogue 访谈对话中口语水平评分的多模态特征分析

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383590

Mao Saeki, Yoichi Matsuyama, Satoshi Kobashikawa, Tetsuji Ogawa, Tetsunori Kobayashi

引用次数: 7