Speech duration is an important component in statistical parameter speech synthesis(SPSS). In LSTM-RNN based SPSS system, the speech duration affects the quality of synthesized speech in two aspects, the prosody of speech and the position features in acoustic model. This paper investigated the effects of duration in LSTM-RNN based SPSS system. The performance of the acoustic models with positio...

Using tagged data from the DARPA Communicator Project, we investigate acoustic features of user responses to system errors. We measure acoustic parameters such as energy, fundamental frequency, sub-band energy, ratios of voiced, unvoiced and silent regions of speech, fundamental frequency slope, spectral slope, and spectral center of gravity. We investigate different types of user responses to ...

This is a study to investigate the parameters of the glottal source signal that are evidenced by three kinds of signals: an electroglottographic (EGG) signal, an acoustic signal, and an oral airflow signal. The glottal pulse waveform, whether intrinsically defined as glotal airflow or area, can be parameterized with attributes that vary across speakers and types of phonation. Some of these para...

This paper presents procedures used for development of a Croatian large vocabulary automatic speech recognition system (LVASR). The proposed acoustic model is based on context-dependent triphone hidden Markov models and Croatian phonetic rules. Different acoustic and language models, developed using a large collection of Croatian speech, are discussed and compared. The paper proposes the best f...

This paper presents a two-stage procedure, based on the Fisher criterion and automatic classi cation trees, for designing acoustic parameters (APs) that target phonetic features in the speech signal. This procedure and a subset of the TIMIT training set were used to develop acoustic parameters for the phonetic features: sonorant, syllabic, strident, palatal, alveolar, labial and velar. Results ...

Porosity is one of the key parameters associated with oil reservoirs. Determination of this petrophysical parameter is an essential step in reservoir characterization. Among different linear and nonlinear prediction tools such as multi-regression and polynomial curve fitting, artificial neural network has gained the attention of researchers over the past years. In the present study, two-dimensi...

A powerful approach for handling uncertainty in observations is to modify the statistical model of the data to appropriately reflect this uncertainty. For the task of noise robust speech recognition, this requires modifying an underlying ”clean” acoustic model to be representative of speech in a particular target acoustic environment. This chapter describes the underlying concepts of model-base...

We design and experimentally demonstrate a broadband yet compact acoustic diode (AD) by using an acoustic nonlinear material and a pair of gain and lossy materials. Due to the capabilities of maintaining the original frequency and high forward transmission while blocking backscattered wave, our design is closer to the desired features of a perfect AD and is promising to play the essential diode...