Teachers often suffer from health problems related to their voice. These problems are related to their working environment, including the acoustics of the lecture rooms. However, there is a lack of studies linking the room acoustic parameters to the voice produced by the speaker. In this pilot study, the main goals are to investigate whether objectively measurable parameters of the rooms can be...

Articulatory inversion is the problem of recovering the sequence of vocal tract shapes that produce a given acoustic speech signal. Traditionally, its difficulty has been attributed to nonuniqueness of the inverse mapping, where different vocal tract shapes can produce the same acoustics. However, evidence for the nonuniqueness has been restricted to theoretical studies, or to data from atypica...

We introduce a framework for speech enhancement based on convolutive non-negative matrix factorization that leverages available speech data to enhance arbitrary noisy utterances with no a priori knowledge of the speakers or noise types present. Previous approaches have shown the utility of a sparse reconstruction of the speech-only components of an observed noisy utterance. We demonstrate that ...

The text-to-speech intonation model we are developing derives from both linguistics, and the acoustics and aerodynamics of speech production. Our underlying premise is that in human speech production there are physical processes intrinsic to speech production, and that some of these processes can be cognitively represented – they can therefore become part of the domain of language processing. T...

We study the sparsity of spectro-temporal representation of speech in reverberant acoustic conditions. This study motivates the use of structured sparsity models for efficient speech recovery. We formulate the underdetermined convolutive speech separation in spectro-temporal domain as the sparse signal recovery where we leverage model-based recovery algorithms. To tackle the ambiguity of the re...

Speech perception requires the effortless mapping from smooth, seemingly continuous changes in sound features into discrete perceptual units, a conversion exemplified in the phenomenon of categorical perception. Explaining how/when the human brain performs this acoustic-phonetic transformation remains an elusive problem in current models and theories of speech perception. In previous attempts t...

It seems a simple and obvious proposition: good hearing and listening conditions are essential for developing good speech, language, and learning skills. Yet, even today, our educators and school planners overlook the importance of effective noise reducing acoustic design in schools. Room acoustics have a significant impact on speech communication. Listening conditions vary in classrooms and of...

Laughter is a nonverbal vocalization that occurs often in speech communication. Since laughter is produced by the speech production mechanism, spectral analysis methods are used mostly for the study of laughter acoustics. In this paper the significance of excitation features for discriminating laughter and speech is discussed. New features describing the excitation characteristics are used to a...

This paper presents our research work of estimating articulatory states and model parameters from speech acoustics. This work represents a prerequisite for a speech recognition system based on articulatory dynamical models. The model parameter estimation was based on the vowels obtained from 590 sentences of 59 speakers from TIMIT speech database, whereas the state estimation experiments have b...

Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Jukka S. Keränen Name of the doctoral dissertation Measurement and Prediction of the Spatial Decay of Speech in Open-Plan Offices Publisher School of Electrical Engineering Unit Department of Signal Processing and Acoustics Series Aalto University publication series DOCTORAL DISSERTATIONS 23/2015 Field of research Acoustics an...