We present constrained time alignment acoustic models based on phonetic knowledge and a speaker independent speech recognition method using our proposed models. Japanese syllable and isolated word recognition experiments show that the models have robustness to intraand interspeaker varieties such as acoustic diversity. Furthermore we experiment with word recognition tests under the condition su...

PURPOSE To analyze the 50% correct recognition data that were from the Wilson et al (this issue) study and that were obtained from 24 listeners with normal hearing; also to examine whether acoustic, phonetic, or lexical variables can predict recognition performance for monosyllabic words presented in speech-spectrum noise. RESEARCH DESIGN The specific variables are as follows: (a) acoustic va...

Spectral/temporal segment features are adapted for isolated word recognition and tested with the entire English alphabet set using Hidden Markov Models. The ISOLET database from OGI and the HTK toolkit from Cambridge university were used to test our feature extraction technique. With our feature set we were able to achieve 97.3% recognition accuracy on test data with one pass using a whole word...

This study examined the temporal dynamics of spoken word recognition in noise and background speech. In two visual-world experiments, English participants listened to target words while looking at four pictures on the screen: a target (e.g. candle), an onset competitor (e.g. candy), a rhyme competitor (e.g. sandal), and an unrelated distractor (e.g. lemon). Target words were presented in quiet,...

Abstract: Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely incorporated in ASR systems to improve their robustness. This paper proposes a novel auditory model which incorporates psychoacoustics and otoacous...

The acoustic cues of the speech signals which are consisted of consonants and vowels are very important for speech perception in noisy competing situations. Since the perception in noise test is one of the valuable measures in the perception/production abilities, so the objective of this study is to determinate a norm for word recognition in white noise (WN) with a signal-to-noise ratio (SNR) b...

This study aimed to investigate differences between ears in performance on a monaural word recognition in noise test among individuals across a broad range of ages assessed for (C)APD. Word recognition scores in quiet and in speech noise were collected retrospectively from the medical files of 107 individuals between the ages of 7 and 30 years who were diagnosed with (C)APD. No ear advantage wa...

A major problem in isolated-word speech recognition systems is detection of the beginning and ending boundaries of the word. It is an essential of speech recognition algorithms, where signal speech segments should be reliably separated. During speech recognition background noise is also recorded, hence the word isolation is difficult. The parametric representation of the speech must provide eno...