2021 IEEE Spoken Language Technology Workshop (SLT)最新文献_第7页

Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR 两阶段增强和自适应CTC融合提高多流端到端ASR鲁棒性

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383621

Ruizhi Li, Gregory Sell, H. Hermansky

{"title":"Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR","authors":"Ruizhi Li, Gregory Sell, H. Hermansky","doi":"10.1109/SLT48900.2021.9383621","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383621","url":null,"abstract":"Performance degradation of an Automatic Speech Recognition (ASR) system is commonly observed when the test acoustic condition is different from training. Hence, it is essential to make ASR systems robust against various environmental distortions, such as background noises and reverberations. In a multi-stream paradigm, improving robustness takes account of handling a variety of unseen single-stream conditions and inter-stream dynamics. Previously, a practical two-stage training strategy was proposed within multi-stream end-to-end ASR, where Stage-2 formulates the multi-stream model with features from Stage-1 Universal Feature Extractor (UFE). In this paper, as an extension, we introduce a two-stage augmentation scheme focusing on mismatch scenarios: Stage-1 Augmentation aims to address single-stream input varieties with data augmentation techniques; Stage-2 Time Masking applies temporal masks on UFE features of randomly selected streams to simulate diverse stream combinations. During inference, we also present adaptive Connectionist Temporal Classification (CTC) fusion with the help of hierarchical attention mechanisms. Experiments have been conducted on two datasets, DIRHA and AMI, as a multi-stream scenario. Compared with the previous training strategy, substantial improvements are reported with relative word error rate reductions of 29.7 − 59.3% across several unseen stream combinations.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"204 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":"114882311","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

Noise-Robust Spoken Language Identification Using Language Relevance Factor Based Embedding 基于语言相关因子嵌入的噪声鲁棒口语识别

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383503

H. Muralikrishna, Shikha Gupta, Dileep Aroor Dinesh, Padmanabhan Rajan

{"title":"Noise-Robust Spoken Language Identification Using Language Relevance Factor Based Embedding","authors":"H. Muralikrishna, Shikha Gupta, Dileep Aroor Dinesh, Padmanabhan Rajan","doi":"10.1109/SLT48900.2021.9383503","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383503","url":null,"abstract":"State-of-the-art systems for spoken language identification (LID) use i-vector or embedding extracted using a deep neural network (DNN) to represent the utterance. These fixed-length representations are obtained without explicitly considering the relevance of individual frame-level feature vectors in deciding the class label. In this paper, we propose a new method to represent the utterance that considers the relevance of the individual frame-level features. The proposed representation can also preserve the locally available LID-specific information in the input features to some extent. To better utilize the local-level information in the new representation, we propose a novel segment-level matching kernel based support vector machine (SVM) classifier. The proposed representation of the utterance based on the relevance of frame-level features improves the robustness of the LID system to different background noise conditions in the speech. The experiments conducted on speech with different background conditions show that the proposed approach performs better than state-of-the-art approaches in noisy speech and performs similarly to the state-of-the-art systems in clean speech condition.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"15 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":"125377807","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

Acoustic Word Embeddings for Zero-Resource Languages Using Self-Supervised Contrastive Learning and Multilingual Adaptation 基于自监督对比学习和多语言适应的零资源语言声学词嵌入

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383594

C. Jacobs, Yevgen Matusevych, H. Kamper

{"title":"Acoustic Word Embeddings for Zero-Resource Languages Using Self-Supervised Contrastive Learning and Multilingual Adaptation","authors":"C. Jacobs, Yevgen Matusevych, H. Kamper","doi":"10.1109/SLT48900.2021.9383594","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383594","url":null,"abstract":"Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoencoder-based re-current models. Another recent approach is to use multilingual transfer: a supervised AWE model is trained on several well-resourced languages and then applied to an unseen zero-resource language. We consider how a recent contrastive learning loss can be used in both the purely unsupervised and multilingual transfer settings. Firstly, we show that terms from an unsupervised term discovery system can be used for contrastive self-supervision, resulting in improvements over previous unsupervised monolingual AWE models. Secondly, we consider how multilingual AWE models can be adapted to a specific zero-resource language using discovered terms. We find that self-supervised contrastive adaptation outperforms adapted multilingual correspondence autoencoder and Siamese AWE models, giving the best overall results in a word discrimination task on six zero-resource languages.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"14 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":"130023951","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: 18

Incorporating Discriminative DPGMM Posteriorgrams for Low-Resource ASR 基于鉴别DPGMM后图的低资源ASR研究

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383597

Bin Wu, S. Sakti, Satoshi Nakamura

{"title":"Incorporating Discriminative DPGMM Posteriorgrams for Low-Resource ASR","authors":"Bin Wu, S. Sakti, Satoshi Nakamura","doi":"10.1109/SLT48900.2021.9383597","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383597","url":null,"abstract":"The first step in building an ASR system is to extract proper speech features. The ideal speech features for ASR must also have high discriminabilities between linguistic units and be robust to such non-linguistic factors as gender, age, emotions, or noise. The discriminabilities of various features have been compared in several Zerospeech challenges to discover linguistic units without any transcriptions, in which the posteriorgrams of DPGMM clustering show strong discriminability and get several top results of ABX discrimination scores between phonemes. This paper appends DPGMM posteriorgrams to increase the discriminability of acoustic features to enhance ASR systems. To the best of our knowledge, DPGMM features, which are usually applied to such tasks as spoken term detection and zero resources tasks, have not been applied to large vocabulary continuous speech recognition (LVCSR) before. DPGMM clustering can dynamically change the number of Gaussians until each one fits one segmental pattern of the whole speech corpus with the highest probability such that the linguistic units of different segmental patterns are clearly discriminated. Our experimental results on the WSJ corpora show our proposal stably improves ASR systems and provides even more improvement for smaller datasets with fewer resources.","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":"134455387","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

Enhancing the Intelligibility of Cleft Lip and Palate Speech Using Cycle-Consistent Adversarial Networks 利用循环一致对抗网络提高唇腭裂语音的可理解性

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383543

Protima Nomo Sudro, Rohan Kumar Das, R. Sinha, S. Prasanna

引用次数: 3

Uncertainty-Aware Representations for Spoken Question Answering 口语问答的不确定性感知表征

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383547

Merve Ünlü Menevşe, E. Arisoy

引用次数: 2

Acoustic Modeling for Multi-Array Conversational Speech Recognition in the Chime-6 Challenge Chime-6挑战中多阵列对话语音识别的声学建模

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383628

Li Chai, Jun Du, Diyuan Liu, Yanhui Tu, Chin-Hui Lee

引用次数: 5

Improving L2 English Rhythm Evaluation with Automatic Sentence Stress Detection 用句子重音自动检测改进二语英语节奏评价

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383455

Binghuai Lin, Liyuan Wang, Hongwei Ding, Xiaoli Feng

{"title":"Improving L2 English Rhythm Evaluation with Automatic Sentence Stress Detection","authors":"Binghuai Lin, Liyuan Wang, Hongwei Ding, Xiaoli Feng","doi":"10.1109/SLT48900.2021.9383455","DOIUrl":"https://doi.org/10.1109/SLT48900.2021.9383455","url":null,"abstract":"English is a stress-timed language, for which sentence stress or prosodic stress plays an important role. It’s then difficult for Chinese who are used to the syllable-timed rhythm to learn the rhythm of English [1]. In this paper, we investigate how to improve the rhythm evaluation based on the sentence stress for Chinese who learn English as a second language (ESL). Particularly, we explore some rhythm measures to quantify rhythmic differences among second language (L2) learners based on sentence stress. To relieve the dependency on labeled data of sentence stress, we predict sentence stress automatically utilizing a hierarchical network with bidirectional Long Short-Term Memory (BLSTM) [2]. We evaluate the proposed method based on the corpus consisting of 3,500 sentences recorded by 100 Chinese speakers aging from 10 to 20 years old, which was marked with the sentence stress labels and scored by three experts. Experimental results show the proposed sentence stress measure is well correlated with labeled prosody scores with a correlation coefficient of −0.73 and the automatic labeling method achieves comparable results with the method with gold labels.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"43 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":"124141293","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: 5

Supervised and unsupervised approaches for controlling narrow lexical focus in sequence-to-sequence speech synthesis 序列到序列语音合成中控制狭窄词汇焦点的监督与非监督方法

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383591

Slava Shechtman, Raul Fernandez, D. Haws

引用次数: 12

Go Beyond Plain Fine-Tuning: Improving Pretrained Models for Social Commonsense 超越简单的微调:改进社会常识的预训练模型

2021 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2021-01-19 DOI: 10.1109/SLT48900.2021.9383453

Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan, Behnam Hedayatnia, Pei Zhou, Dilek Z. Hakkani-Tür

引用次数: 0