One of the major challenges in speech recogntion or any other field, that concerns itself with structured predictions, is the alginment of two different sequences. The training data for training an RNN is a set of utterances, consisting of audio recorded via a regular microphone and the transcription of the spoken words. This transcription may either be in terms of phonemes or characters. It is...

this study sought to investigate the impact of teaching speech acts and role relations through authentic audio-taped and video-taped materials on the level of iranian efl learners’ pragmatic competence. to this end, 55 intermediate learners were ed and randomly assigned to two experimental groups: the audio-taped group and the video-taped group. during the treatment, the audio-taped group recei...

Audio signal classification system analyzes the input audio signal and creates a label that describes the signal at the output. These are used to characterize both music and speech signals. The categorization can be done on the basis of pitch, music content, music tempo and rhythm. The signal classifier analyzes the content of the audio format thereby extracting information about the content fr...

Mapping audio data to feature vectors for the classification, retrieval or identification tasks presents four principal challenges. The dimensionality of the input must be significantly reduced; the resulting features must be robust to likely distortions of the input; the features must be informative for the task at hand; and the feature extraction operation must be computationally efficient. I...

The aim of this paper is to use visual speech information to create Wiener filters for audio speech enhancement. Wiener filters require estimates of both clean speech statistics and noisy speech statistics. Noisy speech statistics are obtained from the noisy input audio while obtaining clean speech statistics is more difficult and is a major problem in the creation of Wiener filters for speech ...

Shake2Talk is a new system for mobile messaging, using gestural input and non-speech audio and tactile output. Users can compose audio-tactile messages through simple gesture interactions and then send them to other users, enabling a range of different types of communication. This paper presents an overview of the Shake2Talk demonstration.

The purpose of this paper is to demonstrate a low bitrate audio coding algorithm that allows modi cations in the compressed domain. The input audio is segregated into three di erent representations: sinusoids, transients, and noise. Each representation can be individually quantized, and then easily be time-scaled and/or

Deep neural networks (DNN) have been successfully applied for music classification tasks including music tagging. In this paper, we investigate the effect of audio preprocessing on music tagging with neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting and scalin...

A system is described which uses the Audio Oracle algorithm for music analysis and machine improvisation. Some improvements on previous Factor Oracle-based systems are presented, including automatic model calibration based on measures fromMusic Information Dynamics, facilities for compositional structuring and automation, and an audio-based query mode which uses the input signal to influence th...