2021 IEEE Spoken Language Technology Workshop (SLT)最新文献_第2页

Using Paralinguistic Information to Disambiguate User Intentions for Distinguishing Phrase Structure and Sarcasm in Spoken Dialog Systems 利用副语言信息消除用户意图歧义在口语对话系统中区分短语结构和讽刺

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383505

Zhengyu Zhou, I. G. Choi, Yongliang He, Vikas Yadav, Chin-Hui Lee

引用次数: 0

Multi-Feature Learning with Canonical Correlation Analysis Constraint for Text-Independent Speaker Verification 基于典型相关分析约束的文本独立说话人验证多特征学习

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383541

Zheng Li, Miao Zhao, Lin Li, Q. Hong

{"title":"Multi-Feature Learning with Canonical Correlation Analysis Constraint for Text-Independent Speaker Verification","authors":"Zheng Li, Miao Zhao, Lin Li, Q. Hong","doi":"10.1109/SLT48900.2021.9383541","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383541","url":null,"abstract":"In order to improve the performance and robustness of text-independent speaker verification systems, various speaker embedding representation learning algorithms have been developed. Typically, exploring manifold kinds of features to describe speaker-related embeddings is a common approach, such as introducing more acoustic features or different resolution scale features. In this paper, a new multi-feature learning strategy with canonical correlation analysis (CCA) constraint is proposed to learn the instinct speaker embeddings, which maximizes the correlation between two features from the same utterance. Based on the multi-feature learning structure, the CCA constraint layer and the CCA loss are utilized to explore the correlation representation between the two kinds of features and alleviate the redundancy. Therefore, two multi-feature learning strategies are studied, using the pairwise acoustic features, and the pair of short-term and long-term features. Furthermore, we improve the long short-term feature learning structure by replacing the LSTM block with the Bidirectional-GRU (B-GRU) block and introducing more dense layers. The effectiveness of these improvements are shown on the VoxCeleb 1 evaluation set, the noisy Vox-Celeb 1 evaluation set and the SITW evaluation set.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"69 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":"116696420","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

Convolution-Based Attention Model With Positional Encoding For Streaming Speech Recognition On Embedded Devices 基于位置编码的卷积注意力模型在嵌入式设备流语音识别中的应用

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383583

Jinhwan Park, Chanwoo Kim, Wonyong Sung

{"title":"Convolution-Based Attention Model With Positional Encoding For Streaming Speech Recognition On Embedded Devices","authors":"Jinhwan Park, Chanwoo Kim, Wonyong Sung","doi":"10.1109/SLT48900.2021.9383583","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383583","url":null,"abstract":"On-device automatic speech recognition (ASR) is much more preferred over server-based implementations owing to its low latency and privacy protection. Many server-based ASRs employ recurrent neural networks (RNNs) to exploit their ability to recognize long sequences with a limited number of states; however, they are inefficient for single-stream implementations in embedded devices. In this study, a highly efficient convolutional model-based ASR with monotonic chunkwise attention is developed. Although temporal convolution-based models allow more efficient implementations, they demand a long filter-length to avoid looping or skipping problems. To remedy this problem, we add positional encoding, while shortening the filter length, to a convolution-based ASR encoder. It is demonstrated that the accuracy of the short filter-length convolutional model is significantly improved. In addition, the effect of positional encoding is analyzed by visualizing the attention energy and encoder outputs. The proposed model achieves the word error rate of 11.20% on TED-LIUMv2 for an end-to-end speech recognition task.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"90 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":"114609393","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: 4

A New Dataset for Natural Language Understanding of Exercise Logs in a Food and Fitness Spoken Dialogue System 食品与健身口语对话系统中运动日志自然语言理解新数据集

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383508

Maya Epps, J. Uribe, M. Korpusik

{"title":"A New Dataset for Natural Language Understanding of Exercise Logs in a Food and Fitness Spoken Dialogue System","authors":"Maya Epps, J. Uribe, M. Korpusik","doi":"10.1109/SLT48900.2021.9383508","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383508","url":null,"abstract":"Health and fitness are becoming increasingly important in the United States, as illustrated by the 70% of adults in the U.S. that are classified as overweight or obese, as well as globally, where obesity nearly tripled since 1975. Prior work used convolutional neural networks (CNNs) to understand a spoken sentence describing one’s meal, in order to expedite the meal-logging process. However, the system lacked a complementary exercise-logging component. We have created a new dataset of 3,000 natural language exercise-logging sentences. Each token was tagged as an Exercise, Feeling, or Other, and mapped to the most relevant exercise, as well as a score of how they felt on a scale from 1 to 10. We demonstrate the following: for intent detection (i.e., logging a meal or exercise), logistic regression achieves over 99% accuracy on a held-out test set; for semantic tagging, contextual embedding models achieve 93% F1 score, outperforming conditional random field models (CRFs); and recurrent neural networks (RNNs) trained on a multiclass classification task successfully map tagged exercise and feeling segments to database matches. By connecting how the user felt while exercising to the food they ate, in the future we may provide personalized and dynamic diet recommendations.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"21 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":"124633370","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

Development of CNN-Based Cochlear Implant and Normal Hearing Sound Recognition Models Using Natural and Auralized Environmental Audio 基于cnn的人工耳蜗和正常听力的自然和听觉环境音频识别模型的开发

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383550

R. Shekar, Chelzy Belitz, J. Hansen

{"title":"Development of CNN-Based Cochlear Implant and Normal Hearing Sound Recognition Models Using Natural and Auralized Environmental Audio","authors":"R. Shekar, Chelzy Belitz, J. Hansen","doi":"10.1109/SLT48900.2021.9383550","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383550","url":null,"abstract":"Restoration of auditory function among hearing impaired individuals using Cochlear Implant (CI) technology has contributed significantly towards an improved quality of life. CI users experience greater challenges in recognizing speech effectively in noisy, reverberant, or time-varying diverse environments. Most CI research efforts focus on enhancing speech perception and environmental sound awareness has received little or no attention. This study focuses on a comparative analysis of normal hearing (NH) vs. CI environmental sound recognition using classifiers trained on learned sound representations using a CNN-based sound event model. Sounds experienced by CI listeners are recreated by auralizing electrical stimuli. CCi-MOBILE is used to generate electrical stimuli and Braecker Vocoder is used for auralization. Natural and auralized sound representations are then applied in order to develop NH and CI sound recognition models. Comparative assessment of environmental sound recognition is carried out by analyzing f1-scores and other performance characteristics. Benefits stemming from this research can help CI researchers improve sound recognition performance, develop novel sound processing algorithms, exclusively for environmental sounds, and identify optimal CI electrical stimulation characteristics to enhance sound perception. Among CI users, improvement in environmental sound awareness contributes to improved quality of life.","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":"131326767","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

Towards Automatic Route Description Unification in Spoken Dialog Systems 语音对话系统中路由描述的自动统一

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383465

Yulan Feng, A. Black, M. Eskénazi

引用次数: 0

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383598

Minguang Song, Yunxin Zhao, Shaojun Wang, Mei Han

引用次数: 3

IDEA: An Italian Dysarthric Speech Database 想法:一个意大利困境语言数据库

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383467

Marco Marini, Mauro Viganò, M. Corbo, M. Zettin, Gloria Simoncini, B. Fattori, Clelia D'Anna, M. Donati, L. Fanucci

{"title":"IDEA: An Italian Dysarthric Speech Database","authors":"Marco Marini, Mauro Viganò, M. Corbo, M. Zettin, Gloria Simoncini, B. Fattori, Clelia D'Anna, M. Donati, L. Fanucci","doi":"10.1109/SLT48900.2021.9383467","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383467","url":null,"abstract":"This paper describes IDEA a database of Italian dysarthric speech produced by 45 speakers affected by 8 different pathologies. Neurologic diagnoses were collected from the subjects’ medical records, while dysarthria assessment was conducted by a speech language pathologist and neurologist. The total number of records is 16794. The speech material consists of 211 isolated common words recorded by a single condenser microphone. The words that refer to an ambient assisted living scenario, have been selected to cover as widely as possible all Italian phonemes.The recordings, supervised by a speech pathologist, were recorded through the RECORDIA software that was developed specifically for this task. It allows multiple recording procedures depending on the patient severity and it includes an electronic record for storing patients’ clinical data. All the recordings in IDEA are annotated with a TextGrid file which defines the boundaries of the speech within the wave file and other types of notes about the record.This paper also includes preliminary experiments on the recorded data to train an automatic speech recognition system from a baseline Kaldi recipe. We trained HMM and DNN models and the results shows 11.75% and 14.99% of WER respectively.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"330 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":"116355447","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: 8

Semi-Supervised end-to-end Speech Recognition via Local Prior Matching 基于局部先验匹配的半监督端到端语音识别

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383552

Wei-Ning Hsu, Ann Lee, Gabriel Synnaeve, Awni Y. Hannun

引用次数: 3

Reed: An Approach Towards Quickly Bootstrapping Multilingual Acoustic Models Reed:快速启动多语言声学模型的方法

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383457

Bipasha Sen, Aditya Agarwal, Mirishkar Sai Ganesh, A. Vuppala

{"title":"Reed: An Approach Towards Quickly Bootstrapping Multilingual Acoustic Models","authors":"Bipasha Sen, Aditya Agarwal, Mirishkar Sai Ganesh, A. Vuppala","doi":"10.1109/SLT48900.2021.9383457","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383457","url":null,"abstract":"Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4× and 7.4× respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean’s multilingual low resource dataset.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"56 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":"125914731","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