Search results for "Speech-Language Pathology"
showing 10 items of 94 documents
Time Difference of Arrival Estimation from Frequency-Sliding Generalized Cross-Correlations Using Convolutional Neural Networks
2020
The interest in deep learning methods for solving traditional signal processing tasks has been steadily growing in the last years. Time delay estimation (TDE) in adverse scenarios is a challenging problem, where classical approaches based on generalized cross-correlations (GCCs) have been widely used for decades. Recently, the frequency-sliding GCC (FS-GCC) was proposed as a novel technique for TDE based on a sub-band analysis of the cross-power spectrum phase, providing a structured two-dimensional representation of the time delay information contained across different frequency bands. Inspired by deep-learning-based image denoising solutions, we propose in this paper the use of convolutio…
Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification
2020
In the last years, deep convolutional neural networks have become a standard for the development of state-of-the-art audio classification systems, taking the lead over traditional approaches based on feature engineering. While they are capable of achieving human performance under certain scenarios, it has been shown that their accuracy is severely degraded when the systems are tested over noisy or weakly segmented events. Although better generalization could be obtained by increasing the size of the training dataset, e.g. by applying data augmentation techniques, this also leads to longer and more complex training procedures. In this article, we propose a new type of pooling layer aimed at …
Evidence for Early Closure Attachment on First Pass Reading Times in French
1997
An eye-tracking experiment was conducted in French with sentences of the form “N V N1of-N2 who …” Example: “A journalist approached the barrister (male) of the singer (female) who seemed more confident (masculine or feminine gender) than (s)he ought to be.” The results are consistent with those of Cuetos and Mitchell (1988). French readers, like Spanish readers, prefer early closure (and are garden-pathed when the sentence turns out to be a late-closure attachment). This effect was exhibited by first-pass reading times that are usually assumed to reflect initial syntactic commitments. These results are discussed in relation to Frazier and Clifton's recent proposals concerning attachment me…
Instrumento para Evaluar la Cohesión Social en Universidades Mexicanas: Resultados de la Validación Cultural UNIVECS-MX
2021
El objetivo de este artículo es ofrecer un instrumento para evaluar la cohesión social en universidades mexicanas. A partir del modelo de evaluación UNIVECS validado en el contexto español, se realiza una adaptación y validación cultural en México; desarrollando un juicio de expertos con nueve profesionales del área de Antropología, Lingüística, Pedagogía, Psicología y Sociología, un jueceo con 51 docentes en educación superior, cuatro grupos de validación de reactivos entre tres universidades con 42 docentes, y un grupo de validación con diez estudiantes universitarios. Todo ello, en función de cuatro criterios de valoración cuantitativa y cualitativa: pertinencia, claridad, factibilidad y…
Spatial and temporal systems in child language and thought: a cross-linguistic study
1999
This research was designed to evaluate the interaction of conceptual and linguistic factors during the acquisition of the spatial and temporal systems of Polish, English and Finnish from 3 to 6 years of age. In the conceptual-spatial task, children reconstructed a layout from a 180-degree change in perspective, and in the conceptual-temporal task they arranged three picture cards in a sequence while telling a story. In the linguistic domain, there were two comprehension tests and one production test containing spatial and temporal contrasts requiring either a single or multiple referent object(s)/event(s). The main effects (i.e., age, dimension, complexity) were always significant. There w…
Aphasia rehabilitation from a pragmatic-functional paradigm. A comparative study of two patients with different performance profiles in natural metal…
2018
Background: The rehabilitation of people with aphasia is a classic research topic, on which different orientations can be observed according to the theory behind the rehabilitation techniques used....
Tonos condicionados por la estructura métrica y pies mínimamente recursivos en Chugach Alutiiq
2016
This article presents a reanalysis of the foot-based phonology of Chugach Alutiiq (henceforth CA), a language that displays a complex mixed ternary–binary rhythm, as well as metrically conditioned distributions of pitch, fortition and vowel lengthening. Elaborating on earlier analyses of CA that had posited some kind of ternary constituent (Hewitt, 1991, 1992; Leer, 1985a, 1985b, 1985c; Rice, 1992), we propose CA should be analyzed by means of the Internally Layered Ternary (ILT) foot, a minimal recursive foot (Prince, 1980; Selkirk, 1980), which was recently revived in a typological study of binary–ternary stress (Martínez-Paricio & Kager, 2015). It will be argued that ILT feet capture CA’…
Effects of finding the speech-language pathologist likeable on postlaryngectomy speech intelligibility outcomes
2021
<b><i>Introduction:</i></b> Speech-language pathologists (SLPs) work with patients after total laryngectomy (TL) to regain verbal communication. The influence of the quality of the therapeutic relationship on the success of TL voice rehabilitation in terms of speech intelligibility is not known. Finding each other likeable is an important factor in establishing and maintaining interpersonal relationships in everyday life. The fit of therapist and client is relevant to the therapeutic relationship. The purpose of this study therefore was to assess the association between the degree of SLPs’ likeability ratings and postlaryngectomy speech intelligibility. <b><…
A case study on feature sensitivity for audio event classification using support vector machines
2016
Automatic recognition of multiple acoustic events is an interesting problem in machine listening that generalizes the classical speech/non-speech or speech/music classification problem. Typical audio streams contain a diversity of sound events that carry important and useful information on the acoustic environment and context. Classification is usually performed by means of hidden Markov models (HMMs) or support vector machines (SVMs) considering traditional sets of features based on Mel-frequency cepstral coefficients (MFCCs) and their temporal derivatives, as well as the energy from auditory-inspired filterbanks. However, while these features are routinely used by many systems, it is not …
Semantic Word Error Rate for Sentence Similarity
2016
Sentence similarity measures have applications in several tasks, including: Machine Translation, Paraphrase Iden- tification, Speech Recognition, Question-answering and Text Summarization. However, measures designed for these tasks are aimed at assessing equivalence rather than resemblance, partly departing from human cognition of similarity. While this is reasonable for these activities, it hinders the applicability of sentence similarity measures to other tasks. We therefore propose a new sentence similarity measure specifically designed for resemblance evaluation, in order to cover these fields better. Experimental results are discussed.