Objective: Many tinnitus patients complain about difficulties regarding speech comprehension. In spite of the high clinical relevance little is known about underlying mechanisms and predisposing factors. Here, we performed an exploratory investigation in a large sample of tinnitus patients to (1) estimate the prevalence of speech comprehension difficulties among tinnitus patients, to (2) compar...

This paper proposes an alternative scheme for extracting speech features in an automatic speech recognition (ASR) system. If an ASR system is trained using a clean speech source, a noisy environment may cause a mismatch between the features from the recognition data and those from the training data. This mismatch deteriorates the recognition accuracy. Thus, unlike in existing speech features, a...

Aim of speech enhancement is to improve the intelligibility and quality of the speech. By recording the speech signal in the noisy environment, clean speech signals are degraded. Speech enhancement reduces the noise without distorting the original (clean) signal. In this concept, Multi-Band Spectral Subtraction (MBSS) method is used to enhance the noisy speech signal. This approach, takes into ...

This paper presents a new method for estimating the nonstationary noise power spectral density given a noisy signal. The method is based on averaging the noisy speech power spectrum using time and frequency dependent smoothing factors. These factors are adjusted based on signal-presence probability in individual frequency bins. Signal presence is determined by computing the ratio of the noisy s...

In this letter, we propose a speech reinforcement technique based on soft decision under both the far-end and near-end noise environments. We amplify the estimated clean speech signal at the far-end based on the estimated ambient noise spectrum at the near-end, as opposed to reinforcing the noisy far-end speech signal, so that it can be heard more intelligibly in far-end noisy environments. To ...

Most current techniques for near-end speech intelligibility enhancement have focused on processing clean input signals, however, in realistic environments, the input is often noisy. Processing noisy speech for intelligibility enhancement using algorithms developed for clean signals can lower the perceptual quality of the samples when they are listened in quiet. Here we address the quality loss ...

This paper presents a new subspace modeling and selection approach for noisy speech recognition. In subspace modeling, we develop factor analysis (FA) for representing noisy speech. FA is a data generation model where the common factors are extracted with factor loading matrix and specific factors. We bridge the connection of FA to signal subspace (SS) approach. Interestingly, FA partitions noi...

w e ppose a new algorithm for enhancing noisy speech which have been degraded by statistically independent additive noise. The al p rithm is based upon modeling the clean speech as a hidden Markov process with mixtures of Gaussian autoregressive (AR) output processes, and the noise process as a sequence of stationary, statistically independent, Gaussian AR vectors. The parameter sets of the mod...

This work proposes a method of speech enhancement that uses a network of HMMs to first decode noisy speech and to then synthesise a set of features that enables a clean speech signal to be reconstructed. Different choices of acoustic model (whole-word, monophone and triphone) and grammars (highly constrained to no constraints) are considered and the effects of introducing or relaxing acoustic a...

Most existing single-channel noise-suppression algorithms cannot improve speech intelligibility for normal-hearing listeners; however, the underlying reason for this performance deficit is still unclear. Given that various speech segments contain different perceptual contributions, the present work assesses whether the intelligibility of noisy speech can be improved when selectively suppressing...