We address issues for improving hands-free speech enhancement and speech recognition performance in different car environments using a single distant microphone. This paper describes a new singlechannel in-car speech enhancement method that estimates the log spectra of speech at a close-talking microphone based on the nonlinear regression of the log spectra of noisy signal captured by a distant...

-In adult readers, parafoveal recognition of words is limited by strong interferences between letters. In the present study subjects were 20 dyslexic children and 20 average readers (9-14 yr). Recognition scores of isolated letters, of embedded letters and of words were compared both in foveal and in parafoveal vision. The groups did equally well on isolated letters whereas the dyslexics genera...

Motivated by a project to create a system for people who are deaf or hard-of-hearing that would use automatic speech recognition (ASR) to produce real-time text captions of spoken English during in-person meetings with hearing individuals, we have augmented a transcript of the Switchboard conversational dialogue corpus with an overlay of word-importance annotations, with a numeric score for eac...

In this paper, we propose a novel method of normalizing the voice quality in an utterance for both clean speech and speech contaminated by noise. The normalization method is applied to the N-best hypotheses from an HMM-based classifier, then an SM (Sub-space Method)-based verifier tests the hypotheses after normalizing the monophone scores together with the HMMbased likelihood score. The HMM-SM...

A complete dialogue system within the task domain of making an appointment is presented. It is based on a semantic network representation of linguistic knowledge and a word recognition system that communicates with the interpretation component bi-directionally. System robustness is achieved using a special meta-score that evaluates the advance of the linguistic interpretation.

Structured tasks are distinctive: each task has its own measure of performance, such as the word error rate in speech recognition, the BLEU score in machine translation, the NDCG score in information retrieval, or the intersection-over-union score in visual object segmentation. This paper presents StructED, a software package for learning structured prediction models with training methods that ...

This dissertation proposes a new automatic speech summarization method through word extraction. In this method, a set of words maximizing a summarization score indicating an appropriateness of summarization is extracted from automatically transcribed speech. This extraction is performed according to a target compression ratio using a dynamic programming technique sentence by sentence. The extra...

The number of pediatric cochlear implant (CI) recipients has increased substantially over the past 10 years, and it has become more important to understand the underlying mechanisms of the variable outcomes in this population. In this study, psychoacoustic measures of spectral-ripple and Schroeder-phase discrimination, the Clinical Assessment of Music Perception, and consonant-nucleus-consonant...

Background: Many elderly individuals complain of difficulty in understanding speech in noise despite having normal hearing thresholds. According to previous studies, auditory training leads to improvement in speech-in-noise perception, but these studies did not consider the etiology, so their results cannot be generalized. The present study aimed at investigating the effectiveness of envelopeba...