We address the learning of noise bases in a monaural speaker-independent speech enhancement framework based on non-negative matrix factorization. Bases are estimated from training data in batch processing by means of hierarchical and non-hierarchical sparse coding, or determined during the speech enhancement process based on the divergence of the observed noisy speech signal and the speech base...

A new method is introduced to perform enhancement of speech degraded by acoustic noise using the psychoacoustic property of masking. The goal of this algorithm is to preserve the natural quality of the noise while keeping the speech perceptually intact. Distortion masking principles based on prior work of Gustafsson are used to derive a hybrid gain function comprising a function minimizing spee...

Current predictors of speech intelligibility are inadequate for understanding and predicting speech confusions caused by acoustic interference. We develop a model of auditory speech processing that includes a phenomenological representation of the action of the Medial Olivocochlear efferent pathway and that is capable of predicting consonant confusions made by normal hearing listeners in speech...

The Mel Frequency cepstral coefficients are the most widely used feature in speech recognition but they are very sensitive to noise. In this paper to achieve a satisfactorily performance in Automatic Speech Recognition (ASR) applications we introduce a noise robust new set of MFCC vector estimated through following steps. First, spectral mean normalization is a pre-processing which applies to t...

The purpose of the study was to examine how teacher motivational practice might influence Iranian EFL Learners’ Request and Refusal Speech Acts Production. To this end, five instruments were used to provide appropriate responses to research questions: (a) Quick Placement Test (b) the Motivational Orientation of Language Teaching classroom observation scheme, (c) the Post-Lesson Teacher Evaluati...

In this paper, a data-driven speech enhancement method based on modeled long-range temporal dynamics (LRTDs) is proposed. First, given speech and noise corpora, Gaussian Mixture Models (GMMs) of the speech and noise can be trained respectively based on the expectation-maximization (EM) algorithm. Then, the LRTDs are obtained from the GMM models. Next, based on the LRTDs, a noise robustness long...

BACKGROUND AND OBJECTIVES This study investigated the effect of ageing on speech perception in quiet and in noise, with noise directed from front, right and left. SUBJECTS AND METHODS Sixty Malay native adults with normal or near normal hearing comprising of 20 young adults (21 to 39 years old), 20 middle aged (40 to 59 years old) and 20 older adults (60 to 74 years old) participated in this ...

This study presents a new approach for robust speech activity detection (SAD). Our framework is based on HMM recognition of speech versus silence. We model speech as one of fourteen large phone classes whereas silence is represented as a separate model. Individual test utterances are concatenated to simulate read continuous speech for testing. The HMM-based algorithm is compared to both an ener...