scholar.google.com › citations
In this paper, we investigate a modified architecture of autoencoder namely, subband autoencoder (SBAE) for representation learning. Features were learned from ...
Using an autoencoder with deformable templates to discover features for automated speech recognition · Computer Science. Interspeech · 2013.
Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine. Conference Paper. Full-text available. Jan 2010.
This website is designed, developed, hosted, and maintained by Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), ...
People also ask
Which technology is used to develop an automatic speech recognition system?
What are the components of automatic speech recognition?
Why don t we use formant frequencies as features for automatic speech recognition?
What is the algorithm for automatic speech recognition?
This paper investigates the use of perceptually-motivated subband temporal envelope (STE) features and time-delay neural network (TDNN) denoising ...
Equal Error Rate · Mel-frequency Cepstral Coefficients · Deep Neural Networks · Spoofing Detection · Automatic Speech Recognition · Spoofed Speech ...
Sep 8, 2016 · Deep Neural Network (DNN) have been extensively used in Automatic Speech Recognition (ASR) applications. Very re- cently, DNNs have also ...
In this paper, we propose to consider Mel sub-band speech processing in denoising auto-encoder(DAE) training to benefit from both mentioned method properties.
Aug 24, 2017 · This paper investigates the use of perceptually-motivated subband temporal envelope (STE) features and time-delay neural network (TDNN) ...
This paper discusses how automatic speech recognition systems are and could be designed, in order to best exploit the discriminative information encoded in ...