Sciweavers

21 search results - page 4 / 5
» Hybrid HMM BLSTM-RNN for Robust Speech Recognition
Sort
View
ICASSP
2011
IEEE
12 years 9 months ago
Large vocabulary continuous speech recognition with context-dependent DBN-HMMS
The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we pro...
George E. Dahl, Dong Yu, Li Deng, Alex Acero
ICASSP
2011
IEEE
12 years 9 months ago
Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR
In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of D...
Oriol Vinyals, Suman V. Ravuri
ICPR
2004
IEEE
14 years 6 months ago
Type-2 Fuzzy Hidden Markov Models to Phoneme Recognition
This paper presents a novel extension of Hidden Markov Models (HMMs): type-2 fuzzy HMMs (type-2 FHMMs). The advantage of this extension is that it can handle both randomness and f...
Jia Zeng, Zhi-Qiang Liu
CIVR
2007
Springer
241views Image Analysis» more  CIVR 2007»
13 years 12 months ago
A robust scene recognition system for baseball broadcast using data-driven approach
We propose a robust scene recognition system for baseball broadcast videos. This system is based on the data-driven approach which has been successful in continuous speech recogni...
Ryoichi Ando, Koichi Shinoda, Sadaoki Furui, Takah...
ICMCS
2005
IEEE
139views Multimedia» more  ICMCS 2005»
13 years 11 months ago
Rapid Feature Space Speaker Adaptation for Multi-Stream HMM-Based Audio-Visual Speech Recognition
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
Jing Huang, Etienne Marcheret, Karthik Visweswaria...