There are subjective and objective acoustic parameters in the creation of performance for speech action room acoustics. Control reverberation time affecting is a main parameter In this study, assessment TOBB Twins Headquarters Reception Hall, which current enclosed space with square plan flat floor, has been performed as case study. The evaluation focused on relationship between interior surfac...

The frequent appearances and varying acoustics of pauses in noisy conversational speech make it a problem to automatically generate an accurate phonetic transcription of the training data for developing robust acoustic models. This paper presents our proposal to exploit reliable phonetic heuristics of pauses in speech to aid the detection of varying pauses. Based on it, a stepwise approach to o...

In a previous study, Arai implemented a sliding vocal-tract model based on Fant’s three-tube model and demonstrated its usefulness for education in acoustics and speech science. The sliding vocal-tract model consists of a long outer cylinder and a short inner cylinder, which simulates tongue constriction in the vocal tract. This model can produce different vowels by sliding the inner cylinder a...

The concept of using visual information as part of audio speech processing has been of significant recent interest. This paper presents a data driven approach that considers estimating audio speech acoustics using only temporal visual information without considering linguistic features such as phonemes and visemes. Audio (log filterbank) and visual (2D-DCT) features are extracted, and various c...

The paper discusses a series of four user-oriented design analysis problems in a research prototype multimodal spoken language dialogue system for supporting drivers whilst driving. The problems are: (a) when should the system (not) listen to the speech and non-speech acoustics in the car; (b) how to use the in-car display in conjunction with spoken driver-system dialogue; (c) how to identify t...

The problem of blindly separating a convolutive mixture of modulated signals is considered. Spectrograms of the signals are computed and separation is performed in the frequency domain. A new algorithm for blind source separation is proposed, which is based on correlated modulation in the sources’ different frequency channels. For example, speech contains correlated modulation in different freq...

Landmark-based software tools are particularly suited to fast, automatic analysis of small, non-lexical differences in production of the same speech material by the same speaker. We are building a suite of independent applications and plugins as toolkits that make our landmark-based software system, SpeechMark, available to the wider scientific community. This will be achieved by extending exis...

Cepstral normalisation in automatic speech recognition is investigated in the context of robustness to additive noise. In this paper, it is argued that such normalisation leads naturally to a speech feature based on signal to noise ratio rather than absolute energy (or power). Explicit calculation of this SNR-cepstrum by means of a noise estimate is shown to have theoretical and practical advan...

We propose a stochastic phoneme space transformation technique that allows the conversion of conditional source phoneme posterior probabilities (conditioned on the acoustics) into target phoneme posterior probabilities. The source and target phonemes can be in any language and phoneme format such as the International Phonetic Alphabet. The novel technique makes use of a Kullback-Leibler diverge...