Shrikant Venkataramani

  • Citations Per Year
Learn More
We present a neural network that can act as an equivalent to a Non-Negative Matrix Factorization (NMF), and further show how it can be used to perform supervised source separation. Due to the extensibility of this approach we show how we can achieve better source separation performance as compared to NMF-based methods, and propose a variety of derivative(More)
Convolutive Non-Negative Matrix Factorization model factorizes a given audio spectrogram using frequency templates with a temporal dimension. In this paper, we present a convolutional auto-encoder model that acts as a neural network alternative to convolutive NMF. Using the modeling flexibility granted by neural networks, we also explore the idea of using a(More)
Single-channel methods for the separation of the lead vocal from mixed audio have traditionally included harmonicsinusoidal modeling and matrix decomposition methods, each with its own strengths and shortcomings. In this work we use a hybrid framework to incorporate prior knowledge about singer and phone identity to achieve the superior separation of the(More)
With mobile phone penetration high and growing rapidly, speech based access to information is an attractive proposition. However, automatic speech recognition(ASR) performance is seriously compromised in real-world scenarios where background acoustic noise is omnipresent. Speech enhancement methods can help to improve the signal quality presented to the(More)
Redubbing is an extensively used technique to correct errors in voiceover recordings. It involves re-recording a part of a voiceover, identifying the corresponding section of audio in the original recording that needs to be replaced, and using low level audio tools to replace the audio. Although this sequence of steps can be performed using traditional(More)
  • 1