Cortical processing of speech and non-speech sounds in adults and newborns

Comprehension of a complex acoustic signal - speech - is vital for human communication, with numerous brain processes required to convert the acoustics into an intelligible message. In four studies in the present thesis, cortical correlates for different stages of speech processing in a mature linguistic system of adults were investigated. In two further studies, developmental aspects of cortical specialisation and its plasticity in adults were examined. In the present studies, electroencephalographic (EEG) and magnetoencephalographic (MEG) recordings of the mismatch negativity (MMN) response elicited by changes in repetitive unattended auditory events and the phonological mismatch negativity (PMN) response elicited by unexpected speech sounds in attended speech inputs served as the main indicators of cortical processes. Changes in speech sounds elicited the MMNm, the magnetic equivalent of the electric MMN, that differed in generator loci and strength from those elicited by comparable changes in non-speech sounds, suggesting intra- and interhemispheric specialisation in the processing of speech and non-speech sounds at an early automatic processing level. This neuronal specialisation for the mother tongue was also reflected in the more efficient formation of stimulus representations in auditory sensory memory for typical native-language speech sounds compared with those formed for unfamiliar, non-prototype speech sounds and simple tones. Further, adding a speech or non-speech sound context to syllable changes was found to modulate the MMNm strength differently in the left and right hemispheres. Following the acoustic-phonetic processing of speech input, phonological effort related to the selection of possible lexical (word) candidates was linked with distinct left-hemisphere neuronal populations. In summary, the results suggest functional specialisation in the neuronal substrates underlying different levels of speech processing. Subsequently, plasticity of the brain's mature linguistic system was investigated in adults, in whom representations for an aurally-mediated communication system, Morse code, were found to develop within the same hemisphere where representations for the native-language speech sounds were already located. Finally, recording and localization of the MMNm response to changes in speech sounds was successfully accomplished in newborn infants, encouraging future MEG investigations on, for example, the state of neuronal specialisation at birth.

Processing of speech signals for physical and sensory disabilities.

Assistive technology involving voice communication is used primarily by people who are deaf, hard of hearing, or who have speech and/or language disabilities. It is also used to a lesser extent by people with visual or motor disabilities. A very wide range of devices has been developed for people with hearing loss. These devices can be categorized not only by the modality of stimulation [i.e., auditory, visual, tactile, or direct electrical stimulation of the auditory nerve (auditory-neural)] but also in terms of the degree of speech processing that is used. At least four such categories can be distinguished: assistive devices (a) that are not designed specifically for speech, (b) that take the average characteristics of speech into account, (c) that process articulatory or phonetic characteristics of speech, and (d) that embody some degree of automatic speech recognition. Assistive devices for people with speech and/or language disabilities typically involve some form of speech synthesis or symbol generation for severe forms of language disability. Speech synthesis is also used in text-to-speech systems for sightless persons. Other applications of assistive technology involving voice communication include voice control of wheelchairs and other devices for people with mobility disabilities.

Report on Workshop on High Performance Computing and Communications for Grand Challenge Applications : computer vision, speech and natural language processing, and artificial intelligence /

Cover title.

The relationship between spoken language and speech and nonspeech processing in children with autism:a magnetic event-related field study

It has been proposed that language impairments in children with Autism Spectrum Disorders (ASD) stem from atypical neural processing of speech and/or nonspeech sounds. However, the strength of this proposal is compromised by the unreliable outcomes of previous studies of speech and nonspeech processing in ASD. The aim of this study was to determine whether there was an association between poor spoken language and atypical event-related field (ERF) responses to speech and nonspeech sounds in children with ASD (n = 14) and controls (n = 18). Data from this developmental population (ages 6-14) were analysed using a novel combination of methods to maximize the reliability of our findings while taking into consideration the heterogeneity of the ASD population. The results showed that poor spoken language scores were associated with atypical left hemisphere brain responses (200 to 400 ms) to both speech and nonspeech in the ASD group. These data support the idea that some children with ASD may have an immature auditory cortex that affects their ability to process both speech and nonspeech sounds. Their poor speech processing may impair their ability to process the speech of other people, and hence reduce their ability to learn the phonology, syntax, and semantics of their native language.

Robust speech recognition using speech enhancement

Automatic Speech Recognition (ASR) has matured into a technology which is becoming more common in our everyday lives, and is emerging as a necessity to minimise driver distraction when operating in-car systems such as navigation and infotainment. In “noise-free” environments, word recognition performance of these systems has been shown to approach 100%, however this performance degrades rapidly as the level of background noise is increased. Speech enhancement is a popular method for making ASR systems more ro- bust. Single-channel spectral subtraction was originally designed to improve hu- man speech intelligibility and many attempts have been made to optimise this algorithm in terms of signal-based metrics such as maximised Signal-to-Noise Ratio (SNR) or minimised speech distortion. Such metrics are used to assess en- hancement performance for intelligibility not speech recognition, therefore mak- ing them sub-optimal ASR applications. This research investigates two methods for closely coupling subtractive-type enhancement algorithms with ASR: (a) a computationally-efficient Mel-filterbank noise subtraction technique based on likelihood-maximisation (LIMA), and (b) in- troducing phase spectrum information to enable spectral subtraction in the com- plex frequency domain. Likelihood-maximisation uses gradient-descent to optimise parameters of the enhancement algorithm to best fit the acoustic speech model given a word se- quence known a priori. Whilst this technique is shown to improve the ASR word accuracy performance, it is also identified to be particularly sensitive to non-noise mismatches between the training and testing data. Phase information has long been ignored in spectral subtraction as it is deemed to have little effect on human intelligibility. In this work it is shown that phase information is important in obtaining highly accurate estimates of clean speech magnitudes which are typically used in ASR feature extraction. Phase Estimation via Delay Projection is proposed based on the stationarity of sinusoidal signals, and demonstrates the potential to produce improvements in ASR word accuracy in a wide range of SNR. Throughout the dissertation, consideration is given to practical implemen- tation in vehicular environments which resulted in two novel contributions – a LIMA framework which takes advantage of the grounding procedure common to speech dialogue systems, and a resource-saving formulation of frequency-domain spectral subtraction for realisation in field-programmable gate array hardware. The techniques proposed in this dissertation were evaluated using the Aus- tralian English In-Car Speech Corpus which was collected as part of this work. This database is the first of its kind within Australia and captures real in-car speech of 50 native Australian speakers in seven driving conditions common to Australian environments.

Spectral coding methods for speech compression and speaker identification

This thesis investigates aspects of encoding the speech spectrum at low bit rates, with extensions to the effect of such coding on automatic speaker identification. Vector quantization (VQ) is a technique for jointly quantizing a block of samples at once, in order to reduce the bit rate of a coding system. The major drawback in using VQ is the complexity of the encoder. Recent research has indicated the potential applicability of the VQ method to speech when product code vector quantization (PCVQ) techniques are utilized. The focus of this research is the efficient representation, calculation and utilization of the speech model as stored in the PCVQ codebook. In this thesis, several VQ approaches are evaluated, and the efficacy of two training algorithms is compared experimentally. It is then shown that these productcode vector quantization algorithms may be augmented with lossless compression algorithms, thus yielding an improved overall compression rate. An approach using a statistical model for the vector codebook indices for subsequent lossless compression is introduced. This coupling of lossy compression and lossless compression enables further compression gain. It is demonstrated that this approach is able to reduce the bit rate requirement from the current 24 bits per 20 millisecond frame to below 20, using a standard spectral distortion metric for comparison. Several fast-search VQ methods for use in speech spectrum coding have been evaluated. The usefulness of fast-search algorithms is highly dependent upon the source characteristics and, although previous research has been undertaken for coding of images using VQ codebooks trained with the source samples directly, the product-code structured codebooks for speech spectrum quantization place new constraints on the search methodology. The second major focus of the research is an investigation of the effect of lowrate spectral compression methods on the task of automatic speaker identification. The motivation for this aspect of the research arose from a need to simultaneously preserve the speech quality and intelligibility and to provide for machine-based automatic speaker recognition using the compressed speech. This is important because there are several emerging applications of speaker identification where compressed speech is involved. Examples include mobile communications where the speech has been highly compressed, or where a database of speech material has been assembled and stored in compressed form. Although these two application areas have the same objective - that of maximizing the identification rate - the starting points are quite different. On the one hand, the speech material used for training the identification algorithm may or may not be available in compressed form. On the other hand, the new test material on which identification is to be based may only be available in compressed form. Using the spectral parameters which have been stored in compressed form, two main classes of speaker identification algorithm are examined. Some studies have been conducted in the past on bandwidth-limited speaker identification, but the use of short-term spectral compression deserves separate investigation. Combining the major aspects of the research, some important design guidelines for the construction of an identification model when based on the use of compressed speech are put forward.