Robust bimodal person identification using face and speech with limited training data and corruption of both modalities

This paper presents a novel method of audio-visual fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there is a limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new representation and a modified cosine similarity are introduced for combining and comparing bimodal features with limited training data as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal data set created from the SPIDRE and AR databases with variable noise corruption of speech and occlusion in the face images. The new method has demonstrated improved recognition accuracy.

An iterative longest matching segment approach to speech enhancement with additive noise and channel distortion

This paper presents a new approach to speech enhancement from single-channel measurements involving both noise and channel distortion (i.e., convolutional noise), and demonstrates its applications for robust speech recognition and for improving noisy speech quality. The approach is based on finding longest matching segments (LMS) from a corpus of clean, wideband speech. The approach adds three novel developments to our previous LMS research. First, we address the problem of channel distortion as well as additive noise. Second, we present an improved method for modeling noise for speech estimation. Third, we present an iterative algorithm which updates the noise and channel estimates of the corpus data model. In experiments using speech recognition as a test with the Aurora 4 database, the use of our enhancement approach as a preprocessor for feature extraction significantly improved the performance of a baseline recognition system. In another comparison against conventional enhancement algorithms, both the PESQ and the segmental SNR ratings of the LMS algorithm were superior to the other methods for noisy speech enhancement.

Speech Enhancement from Additive Noise and Channel Distortion - a Corpus-Based Approach

This paper presents a new approach to single-channel speech enhancement involving both noise and channel distortion (i.e., convolutional noise). The approach is based on finding longest matching segments (LMS) from a corpus of clean, wideband speech. The approach adds three novel developments to our previous LMS research. First, we address the problem of channel distortion as well as additive noise. Second, we present an improved method for modeling noise. Third, we present an iterative algorithm for improved speech estimates. In experiments using speech recognition as a test with the Aurora 4 database, the use of our enhancement approach as a preprocessor for feature extraction significantly improved the performance of a baseline recognition system. In another comparison against conventional enhancement algorithms, both the PESQ and the segmental SNR ratings of the LMS algorithm were superior to the other methods for noisy speech enhancement. Index Terms: corpus-based speech model, longest matching segment, speech enhancement, speech recognition

Merit, Speech Disability and Discrimination

There is a substantial body of evidence – going back over decades – which indicates that the employment sphere is difficult for those who suffer a speech disability. To a large extent, I argue, this is due to the setting of merit in terms of orality and aesthetic. It also relates to the low perception of competence of the speech disabled. I argue that to be effective against discrimination the notion of merit and its assessment requires focus. ‘Merit’ as a concept in discrimination law has had its critics, yet it remains important to investigate it as social construct in order to help understand discrimination and how to counter this. For example, in this article I look at an instance where the resetting of what was viewed as ‘meritorious’ in judicial recruitment successfully improved the diversity in lower judicial posts.

Further, given the relative failure of the employment tribunal system to improve the general position of those who are disabled, I look to alternative methods of countering disability discrimination. The suggestion provided is that an enforced ombudsman type approach capable of dealing with what may be the core issue around employment discrimination (‘merit’) would provide a better mechanism for handling the general situation of disability discrimination than the tribunal system.

Wide Matching - An Approach to Improving Noise Robustness for Speech Enhancement

It is shown that under certain conditions it is possible to obtain a good speech estimate from noise without requiring noise estimation. We study an implementation of the theory, namely wide matching, for speech enhancement. The new approach performs sentence-wide joint speech segment estimation subject to maximum recognizability to gain noise robustness. Experiments have been conducted to evaluate the new approach with variable noises and SNRs from -5 dB to noise free. It is shown that the new approach, without any estimation of the noise, significantly outperformed conventional methods in the low SNR conditions while retaining comparable performance in the high SNR conditions. It is further suggested that the wide matching and deep learning approaches can be combined towards a highly robust and accurate speech estimator.