人教版高中英语新课程教材中,语言运用（Using Language）是每个单元必不可少的部分,提供了围绕单元中心话题的听、说、读、写的综合性练习,是单元中心话题的延续和升华.如何设计Using Language部分的教学,使自己的教学模式既不落俗套,又能真正体现新课程标准所倡导的教学理念,正是广大一线英语教师一直努力探索的问题.

打磨Using Language,倡导新理念

Emotion recognition in human-computer interaction

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn through the formulation of a single auxiliary task like contrastive prediction, autoregressive prediction, or masked reconstruction. Unlike previous approaches, we use a multi-target auxiliary task to pre-train Transformer Encoders on a large amount of unlabeled speech. The model learns through the reconstruction of acoustic frames from its altered counterpart, where we use a stochastic policy to alter along three dimensions: temporal, channel, and magnitude. TERA can be used to extract speech representations or fine-tune with downstream models. We evaluate TERA on several downstream tasks, including phoneme classification, speaker recognition, and speech recognition. TERA achieved strong performance on these tasks by improving upon surface features and outperforming previous methods. In our experiments, we show that through alteration along different dimensions, the model learns to encode distinct aspects of speech. We explore different knowledge transfer methods to incorporate the pre-trained model with downstream models. Furthermore, we show that the proposed method can be easily transferred to another dataset not used in pre-training.

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

Purpose To present an overview of current machine learning methods and their use in medical research, focusing on select machine learning techniques, best practices, and deep learning. Methods A systematic literature search in PubMed was performed for articles pertinent to the topic of artificial intelligence methods used in medicine with an emphasis on ophthalmology. Results A review of machine learning and deep learning methodology for the audience without an extensive technical computer programming background. Conclusions Artificial intelligence has a promising future in medicine; however, many challenges remain. Translational relevance The aim of this review article is to provide the nontechnical readers a layman's explanation of the machine learning methods being used in medicine today. The goal is to provide the reader a better understanding of the potential and challenges of artificial intelligence within the field of medicine.

Introduction to Machine Learning, Neural Networks, and Deep Learning.

E n los últimos años nos hemos acostumbrado a ver soluciones de automatización y control en que la utilización de técnicas de inteligencia artificial aporta beneficios contrastables. Varias marcas comercializan reguladores borrosos o combinados (por ejemplo, PID con control anticipativo borroso), o incluyen mecanismos de ajuste fino de parámetros basados en lógica borrosa. Ocasionalmente, las redes neuronales se han utilizado en el modelado y control de sistemas no lineales. La implantación masiva de sistemas de adquisición y registro de datos (en ocasiones impuestos por requisitos de trazabilidad y calidad) ha permitido un mejor conocimiento de las plantas, que se ha reflejado en las tareas de ingeniería y gestión. Se persigue, por tanto, la reutilización de este conocimiento directamente en planta para detectar y diagnosticar en línea. El beneficio recaerá tanto en la mejora de planes de mantenimiento (ajuste de tiempos, predicción de fallos, asignación de recursos, planificación, etc.) como en la toma de decisiones por parte del supervisor (reducción del tiempo para conocer las causas) para evitar situaciones catastróficas.

A.I. (Inteligencia Artificial)

In the information age, computer applications have become part of modern life and this has in turn encouraged the expectations of friendly interaction with them. Speech, as “the” communication mode, has seen the successful development of quite a number of applications using automatic speech recognition (ASR), including command and control, dictation, dialog systems for people with impairments, translation, etc. But the actual challenge goes beyond the use of speech in control applications or to access information. The goal is to use speech as an information source, competing, for example, with text online. Since the technology supporting computer applications is highly dependent on the performance of the ASR system, research into ASR is still an active topic, as is shown by the range of research directions suggested in (Baker et al., 2009a, 2009b). Automatic speech recognition – the recognition of the information embedded in a speech signal and its transcription in terms of a set of characters, (Junqua & Haton, 1996) – has been object of intensive research for more than four decades, achieving notable results. It is only to be expected that speech recognition advances make spoken language as convenient and accessible as online text when the recognizers reach error rates near zero. But while digit recognition has already reached a rate of 99.6%, (Li, 2008), the same cannot be said of phone recognition, for which the best rates are still under 80% 1,(Mohamed et al., 2011; Siniscalchi et al., 2007). Speech recognition based on phones is very attractive since it is inherently free from vocabulary limitations. Large Vocabulary ASR (LVASR) systems’ performance depends on the quality of the phone recognizer. That is why research teams continue developing phone recognizers, in order to enhance their performance as much as possible. Phone recognition is, in fact, a recurrent problem for the speech recognition community. Phone recognition can be found in a wide range of applications. In addition to typical LVASR systems like (Morris & Fosler-Lussier, 2008; Scanlon et al., 2007; Schwarz, 2008), it can be found in applications related to keyword detection, (Schwarz, 2008), language recognition, (Matejka, 2009; Schwarz, 2008), speaker identification, (Furui, 2005) and applications for music identification and translation, (Fujihara & Goto, 2008; Gruhne et al., 2007). The challenge of building robust acoustic models involves applying good training algorithms to a suitable set of data. The database defines the units that can be trained and

/pdf/phoneme-recognition-on-the-timit-database-1tzln3kr22.pdf

Phoneme Recognition on the TIMIT Database

The objective of this work is to provide a contribution to defect classification. More precisely, we try to prove that it is possible to identify and classify defects of different types using the pulse-echo technique. The classification process makes use of the time and frequency domain responses of the ultrasonic echo signals acquired from different specimens simulating defects with three different shapes (cylindrical, spherical and planar with rectangular cross-section) and sizes. Although the final goal is the characterisation of practical defects (for instance, voids, cracks, delaminations, and so on) appearing in composite materials during manufacturing and in service, we first use the already mentioned reflectors for simplicity reasons. In these experiments 66 reflectors are used with water as matrix material. The inclusion (reflector) materials are brass, copper, steel and polystyrene. From the time domain signals we extract three features, namely, pulse duration, pulse decay rate and peak-to-peak relative amplitude of the third cycle. From the spectra of the echoes we extract the frequency for maximum amplitude and the standard error estimate from the deconvolved spectrum responses. All experimental signals were obtained using only one normal incident ultrasonic transducer aligned to maximise the direct reflected signal. In spite of the fact that this kind of configuration does not provide complete information about the characteristics of the geometries being studied, all the extracted features proved to be important discriminating factors of the geometrical classes considered, as will be demonstrated by making use of a pattern recognition technique for classification.

Automatic defects classification — a contribution

Objective: To early detect nuclear cataract in vivo and automatically classify its severity degree, based on the ultrasound technique, using machine learning. Methods: A 20-MHz ophthalmic ultrasound probe with a focal length of 8.9 mm and an active diameter of 3 mm was used. Twenty-seven features in time and frequency domain were extracted for cataract detection and classification with support vector machine (SVM), Bayes, multilayer perceptron, and random forest classifiers. Fifty rats were used: 14 as control and 36 as study group. An animal model for nuclear cataract was developed. Twelve rats with incipient, 13 with moderate, and 11 with severe cataract were obtained. The hardness of the nucleus and the cortex regions was objectively measured in 12 rats using the NanoTest. Results: Velocity, attenuation, and frequency downshift significantly increased with cataract formation ( $P ). The SVM classifier showed the higher performance for the automatic classification of cataract severity, with a precision, sensitivity, and specificity of 99.7% (relative absolute error of 0.4%). A statistically significant difference was found for the hardness of the different cataract degrees ( $P = 0.016$ ). The nucleus showed a higher hardness increase with cataract formation ( $P = 0.049$ ). A moderate-to-good correlation between the features and the nucleus hardness was found in 23 out of the 27 features. Conclusion: The developed methodology made possible detecting the nuclear cataract in-vivo in early stages, classifying automatically its severity degree and estimating its hardness. Significance: Based on this work, a medical prototype will be developed for early cataract detection, classification, and hardness estimation.

In-Vivo Automatic Nuclear Cataract Detection and Classification in an Animal Model by Ultrasounds

Automatic Cataract Classification based on Ultrasound Technique Using Machine Learning: A comparative Study

Spontaneous speech is full of hesitations, such as fillers, word cut-offs, repetitions and segmental extensions. Automatic identification of such hesitations has several applications; however, it is a challenging research problem. In this paper acoustic-phonetic properties of hesitation phenomena are explored in order to identify and annotate some of these events in a spontaneous speech corpus of Portuguese broadcast television news. Based on pitch, energy, spectral and durational characteristics of the filled pauses and segmental extensions during their production, we intend to characterize the acoustic-phonetic regularity of the phenomena. A speech recognition sys-tem was used to help locating the filled pauses and extensions. The events detected were then manually validated. Our preliminary results suggest that there are regular trends in the production of these hesitation events, which could distinguish them from other events within the structure of Portuguese. Our purpose with this work is to improve acoustic modeling for spontaneous speech recognition systems. Some insights into the process of human speech communication for Portuguese are gained as well.

Fernando Perdigão

Papers

Phoneme Recognition on the TIMIT Database

Automatic defects classification — a contribution

In-Vivo Automatic Nuclear Cataract Detection and Classification in an Animal Model by Ultrasounds

Automatic Cataract Classification based on Ultrasound Technique Using Machine Learning: A comparative Study

Characterization of Hesitations Using Acoustic Models.