21![Structured Output Layer with Auxiliary Targets for Context-Dependent Acoustic Modelling Pawel Swietojanski, Peter Bell, Steve Renals The Centre for Speech Technology Research, University of Edinburgh, United Kingdom {p.s Structured Output Layer with Auxiliary Targets for Context-Dependent Acoustic Modelling Pawel Swietojanski, Peter Bell, Steve Renals The Centre for Speech Technology Research, University of Edinburgh, United Kingdom {p.s](https://www.pdfsearch.io/img/92cff33bee198e07f54f3e3a02d067b0.jpg) | Add to Reading ListSource URL: www.cstr.ed.ac.ukLanguage: English - Date: 2015-09-29 11:06:25
|
---|
22![LDC Forced Aligner Xiaoyi Ma Linguistic Data Consortium 3600 Market St. Suite 810 Philadelphia, PAE-mail: LDC Forced Aligner Xiaoyi Ma Linguistic Data Consortium 3600 Market St. Suite 810 Philadelphia, PAE-mail:](https://www.pdfsearch.io/img/23259b4217b75f915e99486b16d31b4f.jpg) | Add to Reading ListSource URL: www.ldc.upenn.eduLanguage: English - Date: 2013-08-28 15:09:44
|
---|
23![REGULARIZATION OF CONTEXT-DEPENDENT DEEP NEURAL NETWORKS WITH CONTEXT-INDEPENDENT MULTI-TASK TRAINING Peter Bell and Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK ABST REGULARIZATION OF CONTEXT-DEPENDENT DEEP NEURAL NETWORKS WITH CONTEXT-INDEPENDENT MULTI-TASK TRAINING Peter Bell and Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK ABST](https://www.pdfsearch.io/img/a3de6db63743a45f568febb50ff29ba6.jpg) | Add to Reading ListSource URL: www.cstr.ed.ac.ukLanguage: English - Date: 2015-09-29 11:06:25
|
---|
24![Introduction to Multi-Waves Inverse Problems Quantitative Thermo-Acoustic Tomography (QTAT) Discussions on the System Model Quantitative thermo-acoustics and related problems Introduction to Multi-Waves Inverse Problems Quantitative Thermo-Acoustic Tomography (QTAT) Discussions on the System Model Quantitative thermo-acoustics and related problems](https://www.pdfsearch.io/img/8447f37280c3539c8157a4c525f410c4.jpg) | Add to Reading ListSource URL: www.math.purdue.eduLanguage: English - Date: 2012-06-23 13:55:03
|
---|
25![Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition∗ Tavish Vaidya Georgetown University Yuankai Zhang Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition∗ Tavish Vaidya Georgetown University Yuankai Zhang](https://www.pdfsearch.io/img/607087718d0ae5a3e2b3ee14225f56df.jpg) | Add to Reading ListSource URL: security.cs.georgetown.eduLanguage: English - Date: 2015-08-12 11:28:12
|
---|
26![Analysis of CNN-based Speech Recognition System using Raw Speech as Input Dimitri Palaz1,2 , Mathew Magimai.-Doss1 , Ronan Collobert3,1 Idiap Research Institute, Martigny, Switzerland Ecole Polytechnique F´ed´erale de Analysis of CNN-based Speech Recognition System using Raw Speech as Input Dimitri Palaz1,2 , Mathew Magimai.-Doss1 , Ronan Collobert3,1 Idiap Research Institute, Martigny, Switzerland Ecole Polytechnique F´ed´erale de](https://www.pdfsearch.io/img/86d99de581dcad91f0127576698f3bcf.jpg) | Add to Reading ListSource URL: ronan.collobert.comLanguage: English - Date: 2015-06-29 16:44:16
|
---|
27![ALISA: An Automatic Lightly Supervised Speech Segmentation and Alignment ToolI A. Stana,1 , Y. Mamiyab , J. Yamagishia,c , P. Bellb , O. Wattsb , R.A.J. Clarkb , S. Kingb a Communications ALISA: An Automatic Lightly Supervised Speech Segmentation and Alignment ToolI A. Stana,1 , Y. Mamiyab , J. Yamagishia,c , P. Bellb , O. Wattsb , R.A.J. Clarkb , S. Kingb a Communications](https://www.pdfsearch.io/img/db504aabf53da5212f6fd2e5941e8548.jpg) | Add to Reading ListSource URL: www.cstr.ed.ac.ukLanguage: English - Date: 2015-09-29 11:07:00
|
---|
28![MODELLING ACOUSTIC FEATURE DEPENDENCIES WITH ARTIFICIAL NEURAL NETWORKS: TRAJECTORY-RNADE Benigno Uria1 1 Iain Murray1 MODELLING ACOUSTIC FEATURE DEPENDENCIES WITH ARTIFICIAL NEURAL NETWORKS: TRAJECTORY-RNADE Benigno Uria1 1 Iain Murray1](https://www.pdfsearch.io/img/cdf311495a8a3b6be815824e6fa012d1.jpg) | Add to Reading ListSource URL: www.cstr.ed.ac.ukLanguage: English - Date: 2015-09-29 11:06:25
|
---|
29![Wed.P7b.02 Gaussian Map based Acoustic Model Adaptation Using Untranscribed Data for Speech Recognition in Severely Adverse Environments Wed.P7b.02 Gaussian Map based Acoustic Model Adaptation Using Untranscribed Data for Speech Recognition in Severely Adverse Environments](https://www.pdfsearch.io/img/3ba0633d85c246ed9390349e337c2ae9.jpg) | Add to Reading ListSource URL: www.utdallas.eduLanguage: English - Date: 2012-08-21 16:31:46
|
---|
30![AN ADVANCED FEATURE COMPENSATION METHOD EMPLOYING ACOUSTIC MODEL WITH PHONETICALLY CONSTRAINED STRUCTURE Wooil Kim1 and John H. L. Hansen2 1 2 AN ADVANCED FEATURE COMPENSATION METHOD EMPLOYING ACOUSTIC MODEL WITH PHONETICALLY CONSTRAINED STRUCTURE Wooil Kim1 and John H. L. Hansen2 1 2](https://www.pdfsearch.io/img/706644e2db68a5bfc5db3a38106c2e20.jpg) | Add to Reading ListSource URL: www.utdallas.eduLanguage: English - Date: 2013-05-28 13:45:30
|
---|