2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)最新文献_第2页

HiTNet: Byte-to-BPE Hierarchical Transcription Network for End-to-End Speech Recognition 端到端语音识别的字节到bpe分层转录网络

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9687943

Dhananjaya N. Gowda, Abhinav Garg, Jiyeon Kim, Mehul Kumar, Sachin Singh, Ashutosh Gupta, Ankur Kumar, Nauman Dawalatabad, Aman Maghan, Shatrughan Singh, Chanwoo Kim

{"title":"HiTNet: Byte-to-BPE Hierarchical Transcription Network for End-to-End Speech Recognition","authors":"Dhananjaya N. Gowda, Abhinav Garg, Jiyeon Kim, Mehul Kumar, Sachin Singh, Ashutosh Gupta, Ankur Kumar, Nauman Dawalatabad, Aman Maghan, Shatrughan Singh, Chanwoo Kim","doi":"10.1109/ASRU51503.2021.9687943","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9687943","url":null,"abstract":"In this paper, we propose a new byte to byte-pair-encoding (BPE) Hierarchical Transcription Network (HiTNet) architecture for end-to-end (e2e) automatic speech recognition (ASR). The proposed HiTNet architecture simultaneously encodes as well as decodes information hierarchically at different levels of linguistic granularity such as bytes and BPE. In general this idea can be extended to any levels of granularity including phonemes or graphemes or bytes (character to sub-character in some languages), to sub-words or byte-pair encodings (BPE), to words, and so on. Existing hierarchical e2e ASR models primarily encode the acoustic information in an hierarchical manner governed by weaker linguistic constraints at each level. The language information at each level is neither embedded or used explicitly, nor is the information decoded at each level passed on to the next stage. The proposed architecture primarily decodes information in an hierarchical manner utilizing the linguistic information at each level explicitly, while at the same time utilizing the hierarchically encoded acoustic information at each level. Experiments with a two-level byte-to-BPE (b2B) hierarchical transcription show that the proposed architecture significantly reduces the word error rates of both the byte and BPE decoders compared to baseline byte and BPE based attention encoder-decoder models.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131853366","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

Colombian Dialect Recognition Based on Information Extracted from Speech and Text Signals 基于语音和文本信号信息提取的哥伦比亚方言识别

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9687890

D. Escobar-Grisales, C. D. Ríos-Urrego, D. A. López-Santander, J. D. Gallo-Aristizabal, Juan Camilo Vásquez-Correa, E. Nöth, J. Orozco-Arroyave

{"title":"Colombian Dialect Recognition Based on Information Extracted from Speech and Text Signals","authors":"D. Escobar-Grisales, C. D. Ríos-Urrego, D. A. López-Santander, J. D. Gallo-Aristizabal, Juan Camilo Vásquez-Correa, E. Nöth, J. Orozco-Arroyave","doi":"10.1109/ASRU51503.2021.9687890","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9687890","url":null,"abstract":"Dialect recognition is useful in many industrial sectors, par-ticularly with the aim of allowing a better interaction between customers and providers. The core idea is to improve or customize marketing and customer service strategies, de-pending on the geographic location, birthplace and culture. This study proposes different models to automatically dis-criminate between two Colombian dialects: “Antioqueño” and “Bogotano”, to the best of our knowledge this is the first work of Colombian dialect recognition based on real conver-sations from customer service centers. The proposed strategy consists of independent analyses, using information from speech recordings and their corresponding transliterations. On the one hand, classical approaches are used to model speech including prosody features, Mel frequency cepstral coefficients and the mean Hilbert envelope coefficients. For text models, Word2Vec and bidirectional encoding represen-tations from transformer embeddings are considered. On the other hand, a deep learning approach is applied by considering convolutional neural networks, which are trained using spectrograms and embedding matrices for speech and text, respectively. The implemented deep learning models seem to be more promising than the classical ones for the addressed problem. Further experiments will be considered to validate this claim in a wider spectrum of methods.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114246327","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

Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models 利用语言知识实现端到端模型的口音鲁棒性

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9688063

Andrea Carmantini, S. Renals, P. Bell

{"title":"Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models","authors":"Andrea Carmantini, S. Renals, P. Bell","doi":"10.1109/ASRU51503.2021.9688063","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9688063","url":null,"abstract":"Acoustic models are susceptible to the difference in acoustic characteristics between the training distribution and test distributions. Accent variability is a challenging source of variability, and the variations within one accent often do not generalize to others. Consequently, end-to-end models that have only transcriptions as linguistic information need high amounts of data to learn how different accents realize their sounds. To aid with recognition of accented speech, we make use of an accent independent abstraction of phonemes, often called metaphonemes. We force our models to learn hidden representations that are correlated to metaphonemes using multi-task training. Our aim is to obtain a model that is more robust to accented speech and, can, at the same time, adapt faster to different accents through the learned structure. Our experiments on the Common Voice corpus show better generalization when making use of this additional linguistic information, with a word error rate reduction of up to 12.6% when compared to the baseline. Furthermore, the relative improvement when adapting an existing model by making use of the metaphonemes is higher than using Byte Pair Encodings alone.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115088654","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

In Pursuit of Babel - Multilingual End-to-End Spoken Language Understanding 在追求巴别塔-多语言端到端口语理解

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9688263

Markus Müller, Samridhi Choudhary, Clement Chung, A. Mouchtaris

引用次数: 4

ASRU 2021 Organizing Committee ASRU 2021组委会

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/asru51503.2021.9688221

引用次数: 0

A Study of Transducer Based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies 基于换能器的端到端esnet ASR研究:体系结构、辅助损耗和解码策略

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9688251

Florian Boyer, Yusuke Shinohara, Takaaki Ishii, H. Inaguma, Shinji Watanabe

引用次数: 21

Uncertainty-Aware Pseudo-Labeling for Spoken Language Assessment 口语评估中的不确定性感知伪标注

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9687939

Binghuai Lin, Liyuan Wang

引用次数: 0

Applying X-Vectors on Pathological Speech After Larynx Removal x向量在喉切除后病理性言语中的应用

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9688278

Ralph Scheuerer, T. Haderlein, E. Nöth, T. Bocklet

引用次数: 2

Hybrid Network with Multi-Level Global-Local Statistics Pooling for Robust Text-Independent Speaker Recognition 基于多级全局-局部统计池的鲁棒文本独立说话人识别

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/ASRU51503.2021.9687877

Woohyun Kang, J. Alam, A. Fathan

引用次数: 7

[Copyright notice] (版权)

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-12-13 DOI: 10.1109/asru51503.2021.9688158

引用次数: 0