In this study, we investigate an audiovisual approach for classification of vocal outbursts (non-linguistic vocalisations) in noisy conditions using Long Short-Term Memory (LSTM) Recurrent Neural Networks and Support Vector Machines. Fusion of geometric shape features and acoustic low-level descriptors is performed on the feature level. Three different types of acoustic noise are considered: ba...

Native American English and non-native (Dutch) listeners identified either the consonant or the vowel in all possible American English CV and VC syllables. The syllables were embedded in multispeaker babble at three signal-to-noise ratios (0, 8, and 16 dB). The phoneme identification performance of the non-native listeners was less accurate than that of the native listeners. All listeners were ...

OBJECTIVES The purpose of Experiment 1 was to measure word recognition in younger adults with normal hearing when speech or babble was temporally or spectrally distorted. In Experiment 2, older listeners with near-normal hearing and with hearing loss (for pure tones) were tested to evaluate their susceptibility to changes in speech level and distortion types. The results across groups and liste...

Speech enhancement is the task of taking a noisy speech input and producing an enhanced output. In recent years, need for has been increased due to challenges that occurred in various applications such as hearing aids, Automatic Recognition (ASR), mobile communication systems. Most Enhancement research work carried out English, Chinese, other European languages. Only few works involve Indian re...

Stuart Gatehouse was one of the pioneers of cognitive hearing science. The ease of language understanding (ELU) model (Rönnberg) is one example of a cognitive hearing science model where the interplay between memory systems and signal processing is emphasized. The mismatch notion is central to ELU and concerns how phonological information derived from the signal, matches/mismatches phonological...

Four patients who preferred monaural as compared with binaural amplification were evaluated. For these patients, audiometric data, recognition performance on a dichotic digit task, and monaural and binaural hearing aid performance using four amplification strategies (National Acoustic Laboratories-Revised, a speech in noise algorithm, multiple-microphone arrays, and frequency modulated [FM]) ar...

This study aimed to investigate the distracting or masking effects of music tempo and volume, based on subjective evaluation under noise conditions. Two experiments were conducted with 32 participants. In first one, experimental conditions set as follow: (1) sound pressure levels are 45 dB, 60 75 dB; (2) tempos 70 beats per minute (BPM), 110 BPM, 150 BPM; (3) (4) types talkers’ babble, traffic ...

Speech recognition occurs when attending to speech stimuli in auditory, visual, or audiovisual modalities under optimum (e.g., in silence) or degraded listening conditions (i.e., in background noise or in individuals with hearing impairment). The present thesis contains details of the first study to show how background noise (steady-state white noise) delayed the identification of different typ...

We present in this paper a subspace approach for enhancing a noisy speech signal. The original algorithm for model identification from which we have derived our method has been used in the field of fault detection and diagnosis. This algorithm is based on principal component analysis in which the optimal subspace selection is provided by a variance of the reconstruction error (VRE) criterion. T...

This paper presents a new method for robust and accurate fundamental frequency (F0) estimation in the presence of background noise and spectral distortion. Degree of dominance and dominance spectrum are defined based on instantaneous frequencies. The degree of dominance allows one to evaluate the magnitude of individual harmonic components of the speech signals relative to background noise whil...