3. Assess the realism of the talking face. We plan to perform several psychophysical tests to evaluate the realism of our system. 4. Extend our approach using morphable model from TTVS to TTS. We plan to first study morphing of audio sequences. The system will take as input 2 audio sequences, and produce as output intermediate audio sequences that approximate natural exemplars lying between the...

This paper presents new and ongoing development efforts directed toward open-source, cross-platform C++ “tools” for music and audio programming. RtMidi provides a common application programming interface (API) for realtime MIDI input and output on Linux, Windows, Macintosh, and SGI computer systems. RtAudio provides complementary functionality for realtime audio input and output streaming. The ...

This study was an attempt to explore the role that the increased perceptual saliency of L2 input features or output flaws and hereby promoting L2 learners’ noticing (through planned instructional activities) can play in the learners’ use of correct English intonation patterns. The participants were 80 Iranian EFL students attending four intact classes, two low-intermediate and two upper-interme...

This paper describes a system designed to retrieve melodies from a database on the basis of a few notes sung into a microphone. The system first accepts acoustic input from the user, transcribes it into common music notation, then searches a database of 9400 folk tunes for those containing the sung pattern, or patterns similar to the sung pattern; retrieval is ranked according to the closeness ...

We present a model of early word learning which learns from natural audio and visual input. The model has been successfully implemented to learn words and their audio-visual grounding from camera and microphone input. Although simple in its current form, this model is a rst step towards a more complete, fully-grounded model of language acquisition. Practical applications include adaptive human-...

In this study, it was intended to investigate the Persian native speakers’ perception of gerunds by three different elicitation techniques i.e., written, audio, and pictorial through translation. Eighty intermediate learners of English were asked to select Persian translation of the gerund formsin these elicitation techniques. They were asked to choose one option from a pair of written first la...

We present a method that allows novice users to interactively build, design, and edit audio samples using a datadriven synthesis method. With this tool a user can create an audio stream that matches a visual animation using an input sound to provide the qualitative properties of the new sound. The user can easily shape the output to match the desired behavior by specifying sections of the input...

There is a high demand for the delivery of high bitrate streaming media such as video or audio information to all nodes on ad hoc networks. To achieve streaming delivery effectively, we have proposed two novel load-aware flooding methods in which a node decides whether to rebroadcast or not based on information on the MAC transmission queue at the node. Since nodes in ad hoc networks are usuall...

The author presents a system for speech synthesis that selects and concatenates speech segments (units) of various size from an adequately prepared audio-visual speech database. The audio and the video track of selected segments are used together in concatenation to preserve audio-visual correlations. The input text is converted into a target phone chain and the database is searched for appropr...