We present a novel approach to generating photo-realistic images of a face with accurate lip sync, given an audio input. By using a recurrent neural network, we achieved mouth landmarks based on audio features. We exploited the power of conditional generative adversarial networks to produce highly-realistic face conditioned on a set of landmarks. These two networks together are capable of produ...

An audio signal is a representation of sound. Audio signals have frequency range 20 to 20 kHz. Audio signals may be synthesized directly. A mixture refers to the physical combination of two or more substances on which the identities and are mixed in the form to separate out. An audio signal classification system should be able to categorize different audio input formats (speech, background nois...

Existing work has produced a variety of techniques to improve interfaces for navigating an audio timeline. These interfaces typically map user input to either a change in play rate, or playback position. Audio feedback while scrolling at arbitrary rates can be provided by: skipping immediately to the new position in the audio; resampling the audio, which introduces pitch-shifts; timestretching ...

This paper describes the application of Artificial Neural Networks (ANNs) as Data Driven Models (DDMs) to predict urban flooding in real-time based on weather radar and/or raingauge rainfall data. A 123manhole combined sewer sub-network from Keighley, West Yorkshire, UK is used to demonstrate the methodology. An ANN is configured for prediction of flooding at manholes based on rainfall input. I...

The impacts of flooding on socioeconomic outcomes have become a global concern for governments, policymakers, and international organizations alike. situation is particularly challenging in developing nations where poor communities are more vulnerable to the flooding. Consequently, this study investigated impact poverty levels Africa with particular reference Makoko community Lagos State, South...

This paper is a very basic one, where one tries to explain how one can write a digital audio effect in a non-real time situation with a very general mathematical language such as MATLAB, and how such digital audio effects can be used in the real life. 1 What is a digital audio effect? The term « digital audio effects » has been used as an acronym for the COST action G6. So what is a digital aud...

SoundSpotter is an open source software system for real-time matching of an audio input stream to a database of continuous audio or video. Among its novel features are real-time control over audio segmentation, feature selection and match radius. The system uses audio input to control selection of output from a database using similarity-based matching. The low latency methods employed create a ...

This paper proposes a novel approach towards a videorealistic, speech-driven talking face for Cantonese. We present a technique that realizes a talking face for a target language (Cantonese) using only audio-visual facial recordings for a base language (English). Given a Cantonese speech input, we first use a Cantonese speech recognizer to generate a Cantonese syllable transcription. Then we ma...

High quality speech-to-lips conversion, investigated in this work, renders realistic lips movement (video) consistent with input speech (audio) without knowing its linguistic content. Instead of memoryless framebased conversion, we adopt maximum likelihood estimation of the visual parameter trajectories using an audio-visual joint Gaussian Mixture Model (GMM). We propose a minimum converted tra...