Speech Recognition with unknown partial feature corruption - a review of the union model

This paper provides a summary of our studies on robust speech recognition based on a new statistical approach – the probabilistic union model. We consider speech recognition given that part of the acoustic features may be corrupted by noise. The union model is a method for basing the recognition on the clean part of the features, thereby reducing the effect of the noise on recognition. To this end, the union model is similar to the missing feature method. However, the two methods achieve this end through different routes. The missing feature method usually requires the identity of the noisy data for noise removal, while the union model combines the local features based on the union of random events, to reduce the dependence of the model on information about the noise. We previously investigated the applications of the union model to speech recognition involving unknown partial corruption in frequency band, in time duration, and in feature streams. Additionally, a combination of the union model with conventional noise-reduction techniques was studied, as a means of dealing with a mixture of known or trainable noise and unknown unexpected noise. In this paper, a unified review, in the context of dealing with unknown partial feature corruption, is provided into each of these applications, giving the appropriate theory and implementation algorithms, along with an experimental evaluation.

Beyond the Sign. Henri Meschonnic's Poetics of Rhythm and Continuum. Towards an Anthropological Theory of Language

Basing the conception of language on the sign represents also an obstacle to the awareness of certain elements of human life, especially to a full understanding of what language or art do, Henri Meschonnic’s poetics of the continuum and of rhythm criticizes the sign based on Benveniste’s terms of rhythm and discourse, developing an anthropology of language. Rhythm, for Meschonnic, is no formal metrical but a semantic principle, each time unique and unforeseeable. As for Humboldt, his starting point is not the word but the ensemble of speech; language is not ergon but energeia. The poem then is not a literary form but a process of transformation that Meschonnic defines as the invention of a form of life by a form of language and vice versa. Thus a poem is a way of thinking and rhythm is form in movement. The particular subject of art and literature is consequently not the author but a process of subjectivation – this is the contrary of the conception of the sign. By demonstrating the limits of the sign, Meschonnic’s poetics attempts to thematize the intelligibility of presence. Art and literature raise our awareness of this element of human life we cannot grasp conceptually. This poetical thinking is a necessary counterforce against all institutionalization.

Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation

This paper considers the separation and recognition of overlapped speech sentences assuming single-channel observation. A system based on a combination of several different techniques is proposed. The system uses a missing-feature approach for improving crosstalk/noise robustness, a Wiener filter for speech enhancement, hidden Markov models for speech reconstruction, and speaker-dependent/-independent modeling for speaker and speech recognition. We develop the system on the Speech Separation Challenge database, involving a task of separating and recognizing two mixing sentences without assuming advanced knowledge about the identity of the speakers nor about the signal-to-noise ratio. The paper is an extended version of a previous conference paper submitted for the challenge.

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.

Probed serial recall in Williams syndrome: Lexical influences on phonological short-term memory

Williams syndrome is a genetic disorder that, it has been claimed, results in an unusual pattern of linguistic strengths and weaknesses. The current study investigated the hypothesis that there is a reduced influence of lexical knowledge on phonological short-term memory in Williams syndrome. Fourteen children with Williams syndrome and 2 vocabulary la matched control groups, 20 typically developing children and 13 children with learning difficulties, were tested on 2 probed serial-recall tasks. On the basis of previous findings, it was predicted that children with Williams syndrome would demonstrate (a) a reduced effect of lexicality on the recall of list items, (b) relatively poorer recall of list items compared with recall of serial order, and (c) a reduced tendency to produce lexicalization errors in the recall of nonwords. in fact, none of these predictions were supported. Alternative explanations for previous findings and implications for accounts of language development in Williams syndrome are discussed.

Early childhood neurodevelopment after intrauterine growth restriction: a systematic review

BACKGROUND AND OBJECTIVE: Children who experienced intrauterine growth restriction (IUGR) may be at increased risk for adverse developmental outcomes in early childhood. The objective of this study was to carry out a systematic review of neurodevelopmental outcomes from 6 months to 3 years after IUGR.

METHODS: PubMed, Embase, PsycINFO, Maternity and Infant Care, and CINAHL databases were searched by using the search terms intrauterine, fetal, growth restriction, child development, neurodevelopment, early childhood, cognitive, motor, speech, language. Studies were eligible for inclusion if participants met specified criteria for growth restriction, follow-up was conducted within 6 months to 3 years, methods were adequately described, non-IUGR comparison groups were included, and full English text of the article was available. A specifically designed data extraction form was used. The methodological quality of included studies was assessed using well-documented quality-appraisal guidelines.

RESULTS: Of 731 studies reviewed, 16 were included. Poorer neurodevelopmental outcomes after IUGR were described in 11. Ten found motor, 8 cognitive, and 7 language delays. Other delays included social development, attention, and adaptive behavior. Only 8 included abnormal Doppler parameters in their definitions of IUGR.

CONCLUSIONS: Evidence suggests that children are at risk for poorer neurodevelopmental outcomes following IUGR from 6 months to 3 years of age. The heterogeneity of primary outcomes, assessment measures, adjustment for confounding variables, and definitions of IUGR limits synthesis and interpretation. Sample sizes in most studies were small, and some examined preterm IUGR children without including term IUGR or AGA comparison groups, limiting the value of extant studies.

Determining the optimal current direction of transcranial magnetic stimulation to induce motor responses in the tongue: A preliminary study of neurologically healthy individuals

Objective
To determine the optimal transcranial magnetic stimulation (TMS) coil direction for inducing motor responses in the tongue in a group of non-neurologically impaired participants.
Methods
Single-pulse TMS was delivered using a figure-of-eight Magstim 2002 TMS coil. Study 1 investigated the effect of eight different TMS coil directions on the motor-evoked potentials elicited in the tongue in eight adults. Study 2 examined active motor threshold levels at optimal TMS coil direction compared to a customarily-used ventral-caudal direction. Study 3 repeated the procedure of Study 1 at five different sites across the tongue motor cortex in one adult.
Results
Inter-individual variability in optimal direction was observed, with an optimal range of directions determined for the group. Active motor threshold was reduced when a participant's own optimal TMS coil direction was used compared to the ventral-caudal direction. A restricted range of optimal directions was identified across the five cortical positions tested.
Conclusions
There is a need to identify each individual's own optimal TMS coil direction in investigating tongue motor cortex function. A recommended procedure for determining optimal coil direction is described.
Significance
Optimized TMS procedures are needed so that TMS can be utilized in determining the underlying neurophysiological basis of various motor speech disorders.

Technological aids for the rehabilitation of memory and executive functioning in children and adolescents with acquired brain injury (Review).

Background The use of technology in healthcare settings is on the increase and may represent a cost-effective means of delivering rehabilitation. Reductions in treatment time, and delivery in the home, are also thought to be benefits of this approach. Children and adolescents with brain injury often experience deficits in memory and executive functioning that can negatively affect their school work, social lives, and future occupations. Effective interventions that can be delivered at home, without the need for high-cost clinical involvement, could provide a means to address a current lack of provision. We have systematically reviewed studies examining the effects of technology-based interventions for the rehabilitation of deficits in memory and executive functioning in children and adolescents with acquired brain injury. Objectives To assess the effects of technology-based interventions compared to placebo intervention, no treatment, or other types of intervention, on the executive functioning and memory of children and adolescents with acquired brain injury. Search methods We ran the search on the 30 September 2015. We searched the Cochrane Injuries Group Specialised Register, the Cochrane Central Register of Controlled Trials (CENTRAL), Ovid MEDLINE(R), Ovid MEDLINE(R) In-Process & Other Non-Indexed Citations, Ovid MEDLINE(R) Daily and Ovid OLDMEDLINE(R), EMBASE Classic + EMBASE (OvidSP), ISI Web of Science (SCI-EXPANDED, SSCI, CPCI-S, and CPSI-SSH), CINAHL Plus (EBSCO), two other databases, and clinical trials registers. We also searched the internet, screened reference lists, and contacted authors of included studies. Selection criteria Randomised controlled trials comparing the use of a technological aid for the rehabilitation of children and adolescents with memory or executive-functioning deficits with placebo, no treatment, or another intervention. Data collection and analysis Two review authors independently reviewed titles and abstracts identified by the search strategy. Following retrieval of full-text manuscripts, two review authors independently performed data extraction and assessed the risk of bias. Main results Four studies (involving 206 participants) met the inclusion criteria for this review. Three studies, involving 194 participants, assessed the effects of online interventions to target executive functioning (that is monitoring and changing behaviour, problem solving, planning, etc.). These studies, which were all conducted by the same research team, compared online interventions against a 'placebo' (participants were given internet resources on brain injury). The interventions were delivered in the family home with additional support or training, or both, from a psychologist or doctoral student. The fourth study investigated the use of a computer program to target memory in addition to components of executive functioning (that is attention, organisation, and problem solving). No information on the study setting was provided, however a speech-language pathologist, teacher, or occupational therapist accompanied participants. Two studies assessed adolescents and young adults with mild to severe traumatic brain injury (TBI), while the remaining two studies assessed children and adolescents with moderate to severe TBI. Risk of bias We assessed the risk of selection bias as low for three studies and unclear for one study. Allocation bias was high in two studies, unclear in one study, and low in one study. Only one study (n = 120) was able to conceal allocation from participants, therefore overall selection bias was assessed as high. One study took steps to conceal assessors from allocation (low risk of detection bias), while the other three did not do so (high risk of detection bias). Primary outcome 1: Executive functioning: Technology-based intervention versus placebo Results from meta-analysis of three studies (n = 194) comparing online interventions with a placebo for children and adolescents with TBI, favoured the intervention immediately post-treatment (standardised mean difference (SMD) -0.37, 95% confidence interval (CI) -0.66 to -0.09; P = 0.62; I2 = 0%). (As there is no 'gold standard' measure in the field, we have not translated the SMD back to any particular scale.) This result is thought to represent only a small to medium effect size (using Cohen’s rule of thumb, where 0.2 is a small effect, 0.5 a medium one, and 0.8 or above is a large effect); this is unlikely to have a clinically important effect on the participant. The fourth study (n = 12) reported differences between the intervention and control groups on problem solving (an important component of executive functioning). No means or standard deviations were presented for this outcome, therefore an effect size could not be calculated. The quality of evidence for this outcome according to GRADE was very low. This means future research is highly likely to change the estimate of effect. Primary outcome 2: Memory One small study (n = 12) reported a statistically significant difference in improvement in sentence recall between the intervention and control group following an eight-week remediation programme. No means or standard deviations were presented for this outcome, therefore an effect size could not be calculated. Secondary outcomes Two studies (n = 158) reported on anxiety/depression as measured by the Child Behavior Checklist (CBCL) and were included in a meta-analysis. We found no evidence of an effect with the intervention (mean difference -5.59, 95% CI -11.46 to 0.28; I2 = 53%). The GRADE quality of evidence for this outcome was very low, meaning future research is likely to change the estimate of effect. A single study sought to record adverse events and reported none. Two studies reported on use of the intervention (range 0 to 13 and 1 to 24 sessions). One study reported on social functioning/social competence and found no effect. The included studies reported no data for other secondary outcomes (that is quality of life and academic achievement). Authors' conclusions This review provides low-quality evidence for the use of technology-based interventions in the rehabilitation of executive functions and memory for children and adolescents with TBI. As all of the included studies contained relatively small numbers of participants (12 to 120), our findings should be interpreted with caution. The involvement of a clinician or therapist, rather than use of the technology, may have led to the success of these interventions. Future research should seek to replicate these findings with larger samples, in other regions, using ecologically valid outcome measures, and reduced clinician involvement.

Perception of Filtered Speech by Children with Developmental Dyslexia and Children with Specific Language Impairments

Here we use two filtered speech tasks to investigate children’s processing of slow (<4 Hz) versus faster (∼33 Hz) temporal modulations in speech. We compare groups of children with either developmental dyslexia (Experiment 1) or speech and language impairments (SLIs, Experiment 2) to groups of typically-developing (TD) children age-matched to each disorder group. Ten nursery rhymes were filtered so that their modulation frequencies were either low-pass filtered (<4 Hz) or band-pass filtered (22 – 40 Hz). Recognition of the filtered nursery rhymes was tested in a picture recognition multiple choice paradigm. Children with dyslexia aged 10 years showed equivalent recognition overall to TD controls for both the low-pass and band-pass filtered stimuli, but showed significantly impaired acoustic learning during the experiment from low-pass filtered targets. Children with oral SLIs aged 9 years showed significantly poorer recognition of band pass filtered targets compared to their TD controls, and showed comparable acoustic learning effects to TD children during the experiment. The SLI samples were also divided into children with and without phonological difficulties. The children with both SLI and phonological difficulties were impaired in recognizing both kinds of filtered speech. These data are suggestive of impaired temporal sampling of the speech signal at different modulation rates by children with different kinds of developmental language disorder. Both SLI and dyslexic samples showed impaired discrimination of amplitude rise times. Implications of these findings for a temporal sampling framework for understanding developmental language disorders are discussed.

Individual differences in speech and language ability profiles in areas of high deprivation

Speech and language ability is not a unitary concept; rather, it is made up of multiple abilities such as grammar, articulation and vocabulary. Young children from socio-economically deprived areas are more likely to experience language difficulties than those living in more affluent areas. However, less is known about individual differences in language difficulties amongst young children from socio-economically deprived backgrounds. The present research examined 172 four-year-old children from socio-economically deprived areas on standardised measures of core language, receptive vocabulary, articulation, information conveyed and grammar. Of the total sample, 26% had difficulty in at least one area of language. While most children with speech and language difficulty had generally low performance in all areas, around one in 10 displayed more uneven language abilities. For example, some children had generally good speech and language ability, but had specific difficulty with grammar. In such cases their difficulty is masked somewhat by good overall performance on language tests but they could still benefit from intervention in a specific area. The analysis also identified a number of typically achieving children who were identified as having borderline speech and language difficulty and should be closely monitored

Emotional speech: towards a new generation of databases

Research on speech and emotion is moving from a period of exploratory research into one where there is a prospect of substantial applications, notably in human-computer interaction. Progress in the area relies heavily on the development of appropriate databases. This paper addresses the issues that need to be considered in developing databases of emotional speech, and shows how the challenge of developing apropriate databases is being addressed in three major recent projects - the Belfast project, the Reading-Leeds project and the CREST-ESP project. From these and other studies the paper draws together the tools and methods that have been developed, addresses the problems that arise and indicates the future directions for the development of emotional speech databases.

Development of a Java-based Unified and Flexible Natural Language Discourse System

This paper outlines the design and development of a Java-based, unified and flexible natural language dialogue system that enables users to interact using natural language, e.g. speech. A number of software development issues are considered with the aim of designing an architecture that enables different discourse components to be readily and flexibly combined in a manner that permits information to be easily shared. Use of XML schemas assists this component interaction. The paper describes how a range of Java language features were employed to support the development of the architecture, providing an illustration of how a modern programming language makes tractable the development of a complex dialogue system.