Filters








620 Hits in 8.2 sec

Maximal Figure-of-Merit Framework to Detect Multi-label Phonetic Features for Spoken Language Recognition

Ivan Kukanov, Trung Trong, Ville M. Hautamaki, Sabato Marco Siniscalchi, Valerio Salerno, Kong Aik Lee
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rut5unc4enborm7fhpkwgeza7m" style="color: black;">IEEE/ACM Transactions on Audio Speech and Language Processing</a> </i> &nbsp;
Figure of Merit (MFoM) objective.  ...  We use manner and place of articulation as speech attributes, which lead to low-dimensional "universal" phonetic features that can be defined across all spoken languages.  ...  It combines the knowledge gained from our previous work with the maximal figure-of-merit mathematical framework (MFoM), multi-label acoustic event detection, and speech articulatory features into a single  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2020.2964953">doi:10.1109/taslp.2020.2964953</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mbgnpquuejbb5iai2icigvu7um">fatcat:mbgnpquuejbb5iai2icigvu7um</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108163516/https://ieeexplore.ieee.org/ielx7/6570655/8938144/08952610.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/31/a0/31a09f0e157e69b28e02e6d8b00565b3c83c7150.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2020.2964953"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Recent developments in spoken term detection: a survey

Anupam Mandal, K. R. Prasanna Kumar, Pabitra Mitra
<span title="2013-12-14">2013</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xeix3cke4vgplj7qtbgmiixzka" style="color: black;">International Journal of Speech Technology</a> </i> &nbsp;
Spoken term detection (STD) provides an efficient means for content based indexing of speech.  ...  However, achieving high detection performance, faster speed, detecting ot-of-vocabulary (OOV) words and performing STD on low resource languages are some of the major research challenges.  ...  Keshet et al. (2007) proposed a training algorithm to directly maximize the Figure- of-Merit criteria typically used to evaluate the performance of keyword spotters.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10772-013-9217-1">doi:10.1007/s10772-013-9217-1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wdegow7dezc65osihpjhittgou">fatcat:wdegow7dezc65osihpjhittgou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810031256/http://cse.iitkgp.ac.in/~pabitra/paper/ijst13.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/84/4d/844d793500e14293323032e43380a9e9a71c0f79.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10772-013-9217-1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Table of Contents

<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rut5unc4enborm7fhpkwgeza7m" style="color: black;">IEEE/ACM Transactions on Audio Speech and Language Processing</a> </i> &nbsp;
Wang 2109 (Contents Continued on Page vi) 671 Maximal Figure-of-Merit Framework to Detect Multi-Label Phonetic Features for Spoken Language 852 Cognitive-Driven Binaural Beamforming Using EEG-Based  ...  Chen 1183 Out-of-Domain Detection for Natural Language Understanding in Dialog Systems . , and R. M.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2020.3046148">doi:10.1109/taslp.2020.3046148</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hirdphjf6zeqdjzwnwlwlamtb4">fatcat:hirdphjf6zeqdjzwnwlwlamtb4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429144801/https://ieeexplore.ieee.org/ielx7/6570655/8938144/09311743.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/13/1e/131ea0adf9d0c3a67a2079459a30f34e0934d581.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2020.3046148"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Subspace-based phonotactic language recognition using multivariate dynamic linear models

Hung-Shin Lee, Yu-Chin Shih, Hsin-Min Wang, Shyh-Kang Jeng
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rc5jnc4ldvhs3dswicq5wk3vsq" style="color: black;">2013 IEEE International Conference on Acoustics, Speech and Signal Processing</a> </i> &nbsp;
Phonotactics, dealing with permissible phone patterns and their frequencies of occurrence in a specific language, is acknowledged to be related to spoken language recognition (SLR) no matter the subject  ...  The results of SLR experiments on the OGI-TS corpus demonstrate that the proposed framework outperforms the well-known vector space modeling (VSM)-based methods and achieves comparable performance to our  ...  The springing up of a variety of multi-lingual services brought about the birth of automatic spoken language recognition (SLR), which is the process of identifying or verifying the language spoken in a  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2013.6638993">doi:10.1109/icassp.2013.6638993</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icassp/LeeSWJ13.html">dblp:conf/icassp/LeeSWJ13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lkffrgtwjvbzvgq2hpg4akqbpu">fatcat:lkffrgtwjvbzvgq2hpg4akqbpu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809035154/http://www.iis.sinica.edu.tw/papers/whm/15913-F.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0f/b2/0fb2e22ae756e930211dae592a45a6a181a824f5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2013.6638993"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

An Extensive Review of Feature Extraction Techniques, Challenges and Trends in Automatic Speech Recognition

Vidyashree Kanabur, Sunil S Harakannanavar, Dattaprasad Torse
<span title="2019-05-08">2019</span> <i title="MECS Publisher"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7hgv6dkr7vaq7mvfy3joc3nu2y" style="color: black;">International Journal of Image Graphics and Signal Processing</a> </i> &nbsp;
In order to recognize the areas of further research in ASR, one must be aware of the current approaches, challenges faced by each and issues that needs to be addressed.  ...  This task is achieved by Automatic Speech Recognition (ASR) system which is typically a speech-to-text converter.  ...   Useful for multi-speaker and multi-languages  Reliable for moderate to high sized vocabulary  It is easy to implement.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5815/ijigsp.2019.05.01">doi:10.5815/ijigsp.2019.05.01</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3uidt4wvofffvmuqlnanaegzjq">fatcat:3uidt4wvofffvmuqlnanaegzjq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200214050331/http://www.mecs-press.org/ijigsp/ijigsp-v11-n5/IJIGSP-V11-N5-1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/78/4d/784d625c86358679467e849f1de2018db99be103.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5815/ijigsp.2019.05.01"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

Aren Jansen, Emmanuel Dupoux, Sharon Goldwater, Mark Johnson, Sanjeev Khudanpur, Kenneth Church, Naomi Feldman, Hynek Hermansky, Florian Metze, Richard Rose, Mike Seltzer, Pascal Clark (+15 others)
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rc5jnc4ldvhs3dswicq5wk3vsq" style="color: black;">2013 IEEE International Conference on Acoustics, Speech and Signal Processing</a> </i> &nbsp;
Centered around the tasks of phonetic and lexical discovery, we consider unified evaluation metrics, present two new approaches for improving speaker independence in the absence of supervision, and evaluate  ...  language acquisition.  ...  Below we describe two such efforts in large vocabulary recognition and spoken term detection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2013.6639245">doi:10.1109/icassp.2013.6639245</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13.html">dblp:conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4lrcendhhjgz5nmr2fsovmzgae">fatcat:4lrcendhhjgz5nmr2fsovmzgae</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171117090639/https://core.ac.uk/download/pdf/28975847.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4e/95/4e95169fe1f9bdd15fc47bf56d661f6879a94d4f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2013.6639245"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Speech Retrieval [chapter]

Ciprian Chelba, Timothy J. Hazen, Bhuvana Ramabhadran, Murat Saraçlar
<span title="2011-03-23">2011</span> <i title="John Wiley &amp; Sons, Ltd"> Spoken Language Understanding </i> &nbsp;
The primary technical challenges of speech retrieval lie in the retrieval system's ability to deal with imperfect speech recognition technology that produces errorful output due to misrecognitions cause  ...  In this chapter we discuss the retrieval and browsing of spoken audio documents.  ...  Direct maximization of the figure of merit, which is defined as the expected rate of detected search term occurrences over operating regions with a low false alarm rate is performed by training the parameters  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1002/9781119992691.ch15">doi:10.1002/9781119992691.ch15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o36ulm7kh5dxvhm6alb4yz3qvy">fatcat:o36ulm7kh5dxvhm6alb4yz3qvy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829222245/https://ll.mit.edu/mission/cybersec/publications/publication-files/book_chapter/2011_05_03_Hazen_Speech_Retrieval_FP.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c4/fd/c4fd10dc3f88d1869ffccadc5926370d21855396.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1002/9781119992691.ch15"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> wiley.com </button> </a>

Acoustic-Phonetic Approaches for Improving Segment-Based Speech Recognition for Large Vocabulary Continuous Speech

Krerksak Likitsupin, Proadpran Punyabukkana, Chai Wutiwiwatchai, Atiwong Suchato
<span title="2016-05-18">2016</span> <i title="Faculty of Engineering, Chulalongkorn University"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ru3yy36s65cnhkah276jjvkz6e" style="color: black;">Engineering Journal</a> </i> &nbsp;
Another aspect of improvement to our segment-based framework tackles the restriction of having limited amount of training speech data which prevents the usage of more complex covariance matrices for the  ...  An aspect of this research focuses on determining the missing segments due to missed detection of segment boundaries.  ...  Acknowledgements This research was supported by the Thailand Graduate Institute of Science and Technology (grant no. TG-44-09-088D).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4186/ej.2016.20.2.179">doi:10.4186/ej.2016.20.2.179</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/be2pdbedffa6xpvdk3mlr22p6i">fatcat:be2pdbedffa6xpvdk3mlr22p6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180721164025/http://www.engj.org/index.php/ej/article/download/847/456/" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7b/a0/7ba02772373c25a1dd4ad4830ab50212f77b99a9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4186/ej.2016.20.2.179"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

2020 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28

<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rut5unc4enborm7fhpkwgeza7m" style="color: black;">IEEE/ACM Transactions on Audio Speech and Language Processing</a> </i> &nbsp;
., +, TASLP 2020 402-415 B Backpropagation Maximal Figure-of-Merit Framework to Detect Multi-Label Phonetic Features for Spoken Language Recognition.  ...  ., +, TASLP 2020 964-975 Subspace-Based Representation and Learning for Phonotactic Spoken Language Recognition.  ...  T Target tracking Multi-Hypothesis Square-Root Cubature Kalman Particle Filter for Speaker Tracking in Noisy and Reverberant Environments. Zhang, Q., +, TASLP 2020 1183 -1197  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2021.3055391">doi:10.1109/taslp.2021.3055391</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7vmstynfqvaprgz6qy3ekinkt4">fatcat:7vmstynfqvaprgz6qy3ekinkt4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210218100609/https://ieeexplore.ieee.org/ielx7/6570655/8938144/09352987.pdf?tp=&amp;arnumber=9352987&amp;isnumber=8938144&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/48/5a/485a74dc9066974fdf8cc3ec000abfaa0f4ffd37.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2021.3055391"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Subword-based approaches for spoken document retrieval

Kenney Ng, Victor W. Zue
<span title="">2000</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yx5bmukg7revlpm4yd5obfwtsa" style="color: black;">Speech Communication</a> </i> &nbsp;
The use of subword units in the recognizer constrains the size of the vocabulary needed to cover the language; and the use of subword units as indexing terms allows for the detection of new user-specified  ...  Next, we develop a phonetic speech recognizer and process the spoken document collection to generate phonetic transcriptions.  ...  In (Wechsler et al. 1998 ), a word spotting technique that allows for phone mismatches is used to detect query terms in the errorful phonetic transcriptions of the spoken documents.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0167-6393(00)00008-x">doi:10.1016/s0167-6393(00)00008-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4jig4v5w25gqpjmbej6k2x2byq">fatcat:4jig4v5w25gqpjmbej6k2x2byq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180725182206/http://dspace.mit.edu/bitstream/handle/1721.1/16737/45156861-MIT.pdf;jsessionid=BCE41F4C88838828700D8462A7E4B7FF?sequence=2" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/44/48/4448c91b2fc054dc1b0813392cd4aab37bc9644c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0167-6393(00)00008-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

VOICECONET: A Collaborative Framework for Speech-Based Computer Accessibility with a Case Study for Brazilian Portuguese [chapter]

Nelson Neto, Pedro Batista, Aldebaro Klautau
<span title="2012-11-28">2012</span> <i title="InTech"> Modern Speech Recognition Approaches with Case Studies </i> &nbsp;
Evaluation metrics In most ASR applications the figure of merit of an ASR system is the word error rate (WER).  ...  Another feature allows context-dependent language model to be created.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/47835">doi:10.5772/47835</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uy4jtkdgg5hdnc3p4tvhphqydq">fatcat:uy4jtkdgg5hdnc3p4tvhphqydq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170815033603/http://cdn.intechopen.com/pdfs-wm/41208.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/71/db/71dbe5a137ac4135309494d4a71222f9136e25f8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/47835"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A Bottom-Up Modular Search Approach to Large Vocabulary Continuous Speech Recognition

S. M. Siniscalchi, Torbjorn Svendsen, Chin-Hui Lee
<span title="">2013</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zcz4ey2iwffxtgaodtf5jtebmy" style="color: black;">IEEE Transactions on Audio, Speech, and Language Processing</a> </i> &nbsp;
As for word recognition, the proposed WFSM-based framework achieves encouraging word error rates.  ...  A novel bottom-up decoding framework for large vocabulary continuous speech recognition (LVCSR) with a modular search strategy is presented.  ...  Chen, for their assistance during the setup of the large-memory workstations at Georgia Institute of Technology.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tasl.2012.2234115">doi:10.1109/tasl.2012.2234115</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zhlrzldc3jba7cjavofzvqmqzq">fatcat:zhlrzldc3jba7cjavofzvqmqzq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809224106/http://ttic.uchicago.edu/~haotang/speech/06384711.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0d/b6/0db625ac9456078ce59f4a51086eeb33adddf60f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tasl.2012.2234115"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval

Lin-shan Lee, James Glass, Hung-yi Lee, Chun-an Chan
<span title="">2015</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rut5unc4enborm7fhpkwgeza7m" style="color: black;">IEEE/ACM Transactions on Audio Speech and Language Processing</a> </i> &nbsp;
This challenge leads to the emergence of another approach to spoken content retrieval: to go beyond the basic framework of cascading ASR with text retrieval in order to have retrieval performances that  ...  Spoken content retrieval has been very successfully achieved with the basic approach of cascading automatic speech recognition (ASR) with text information retrieval: after the spoken content is transcribed  ...  For the experiments of STD on Fisher corpus, the model thus learned yielded 11% relative improvements in terms of Figure of Merit (FOM) over the baseline without transformation [140] . D.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2015.2438543">doi:10.1109/taslp.2015.2438543</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hwrwmwtlkzfbfagox7bazu5r6a">fatcat:hwrwmwtlkzfbfagox7bazu5r6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830013303/http://groups.csail.mit.edu/sls/publications/2015/Glass_IEEE-15.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cf/ea/cfea91c3db43ab0a0f6573cfa9e804270ac942ed.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2015.2438543"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

The use of subword linguistic modeling for multiple tasks in speech recognition

Stephanie Seneff
<span title="">2004</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yx5bmukg7revlpm4yd5obfwtsa" style="color: black;">Speech Communication</a> </i> &nbsp;
The re-9 search is most specifically aimed at the difficult task of identifying and characterizing unknown words, although the 10 proposed framework also has utility in other recognition tasks such as  ...  These include phonological modeling, hierarchical duration modeling, sound-to-letter 17 and letter-to-sound mapping, and automatic acquisition of unknown words in a speech understanding system.  ...  Results were re-666 ported in terms of a ''figure of merit'' (FOM), 667 derived by integrating over a receiver operator 668 characteristic (ROC) curve, which gives detection 669 rate as a function of false  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.specom.2003.11.001">doi:10.1016/j.specom.2003.11.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vhpz4mir2vhlthfjbo23doc5sy">fatcat:vhpz4mir2vhlthfjbo23doc5sy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830054856/http://groups.csail.mit.edu/sls//publications/2004/angie-speech-comm04.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/51/dc/51dc3c999dfa38d9affbe9dd06601484bad1432c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.specom.2003.11.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

COSMO-Onset: A Neurally-Inspired Computational Model of Spoken Word Recognition, Combining Top-Down Prediction and Bottom-Up Detection of Syllabic Onsets

Mamady Nabé, Jean-Luc Schwartz, Julien Diard
<span title="2021-08-04">2021</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/j33hgvvadjhazfxeupgxga54ai" style="color: black;">Frontiers in Systems Neuroscience</a> </i> &nbsp;
We show that, while purely bottom-up onset detection is sufficient for word recognition in nominal conditions, top-down prediction of syllabic onset events allows overcoming challenging adverse conditions  ...  We present a new probabilistic model of spoken word recognition, called COSMO-Onset, in which syllabic parsing relies on fusion between top-down, lexical prediction of onset events and bottom-up onset  ...  All authors contributed to the article and approved the submitted version.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnsys.2021.653975">doi:10.3389/fnsys.2021.653975</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dz7a5cnxr5ardla5nrm4dorljy">fatcat:dz7a5cnxr5ardla5nrm4dorljy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220203113319/https://hal.archives-ouvertes.fr/hal-03318691/file/nabe%CC%8121.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/21/75/2175c6cf179ca230537254cbfaab44ccac4c2965.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnsys.2021.653975"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 620 results