Conferences
About us
Login
Sign up
Conferences
/
SAPA SCALE Conference 2012
/
Hierarchical Hybrid Language Models for Open Vocabulary Continuous Speech Recognition using WFST
Player is loading...
Info
Embed
Hierarchical Hybrid Language Models for Open Vocabulary Continuous Speech Recognition using WFST
M. Ali Basha Shaik, RWTH Aachen University
Friday, Sept. 7, 2012 · 3:36 p.m. · 24m 55s
Embed
Copy embed code
Player is loading...
Share this talk:
Start at:
Stop at:
Share on Twitter
Conference Program
20:02
Pitch Estimation Using Mutual Information
Yanbo Xu, University of Maryland College Park
Sept. 7, 2012 · 11:07 a.m.
30:16
Establishing some principles of human speech production through two-dimensional computational models
Mauro Nicolao, University of Sheffield
Sept. 7, 2012 · 11:31 a.m.
49:32
Human sound perception - what can we learn from it when developing audio analysis algorithms?
Tuomas Virtanen, Tampere University of Technology
Sept. 7, 2012 · 11:46 a.m.
188
views
20:14
A Spectral Envelope Estimation Method Based on F0-Adaptive Multi-Frame Integration Analysis
Tomoyasu Nakano, AIST
Sept. 7, 2012 · 1:02 p.m.
143
views
18:48
Cochlear Implant-like Processing of Speech Signal for Speaker Verification
Cong-Thanh Do, LIMSI-CNRS/Universite Paris-Sud
Sept. 7, 2012 · 1:14 p.m.
18:48
Speech intelligibility enhancement for HMM-based synthetic speech in noise
Cassia Valentini-Botinhao, University of Edinburgh
Sept. 7, 2012 · 1:37 p.m.
160
views
26:09
A Generalized Stein's Estimation Approach for Speech Enhancement Based on Perceptual Criteria
Sunder Ram Krishnan, Indian Institute of Science
Sept. 7, 2012 · 2:02 p.m.
13:54
Template-based ASR using Posterior features and Synthetic References: comparing different TTS systems
Serena Soldo, Idiap Research Institute
Sept. 7, 2012 · 2:04 p.m.
15:48
Explicit Duration Modelling in HMM-based Speech Synthesis using a Hybrid Hidden Markov Model-Multilayer Perceptron
Kalu U. Ogbureke, University College Dublin
Sept. 7, 2012 · 2:26 p.m.
104
views
22:31
Non-Stationary Signal Processing and its Application in Speech Recognition
Zoltán Tüske, RWTH Aachen University
Sept. 7, 2012 · 2:29 p.m.
135
views
15:35
Joint Uncertainty Decoding with Unscented Transform for Noise Robust Subspace Gaussian Mixture Models
Liang Lu, University of Edinburgh
Sept. 7, 2012 · 3:16 p.m.
24:55
Hierarchical Hybrid Language Models for Open Vocabulary Continuous Speech Recognition using WFST
M. Ali Basha Shaik, RWTH Aachen University
Sept. 7, 2012 · 3:36 p.m.
22:18
Language Identification using Spectro-Temporal Patch features
Kamal Sahn, CMU
Sept. 8, 2012 · 11:06 a.m.
144
views
19:22
Joint Detection and Localization of Multiple Speakers using a Probabilistic Steered Response Power
Youssef Oualil, Saarland University/Idiap
Sept. 8, 2012 · 11:31 a.m.
139
views
02:28
Joint Detection and Localization of Multiple Speakers using a Probabilistic Steered Response Power (part 2)
Youssef Oualil, Saarland University/Idiap
Sept. 8, 2012 · 11:50 a.m.
17:19
Structured Sparse Coding for Microphone Array Location Calibration
Afsaneh Asaei, Idiap/CMU
Sept. 8, 2012 · 11:55 a.m.
208
views
22:18
Inharmonic Speech: A Tool for the Study of Speech Perception and Separation
Dan Ellis, NYU/Columbia/Wakayama
Sept. 8, 2012 · 1:19 p.m.
15:50
Multi-Channel Speech Separation with Soft Time-Frequency Masking
Friedrich Faubel , Saarland University
Sept. 8, 2012 · 1:48 p.m.
219
views
18:50
Smoothing Speech Trajectories by Regularization
Louis ten Bosch, Radboud University Nijmegen
Sept. 8, 2012 · 2:06 p.m.
207
views
20:38
Data-driven Speech Representations for NMF-based Word Learning
Hugo Van hamme, KU Leuven
Sept. 8, 2012 · 2:51 p.m.
291
views
24:44
Spectro-Temporal Features with Distribution Equalization
Samuel K. Ngouoko M. , Bielefeld University/Honda Research
Sept. 8, 2012 · 3:18 p.m.
117
views
17:22
Log-normal matrix factorization with application to speech-music separation
Takuya Yoshioka, Sakaue Daichi, NTT Communication Science Laboratories
Sept. 8, 2012 · 3:46 p.m.
198
views
Recommended talks
10:45
Bridging the Gap between ASR and HSR (AHSR)
Liang Lu, University of Edinburgh, UK
June 21, 2012 · 11:32 a.m.
17:17
Questions & Answers of Session 2
March 7, 2012 · 4:52 p.m.