Search results for "speech"
showing 10 items of 1281 documents
Effects of Global and Local Contexts on Harmonic Expectancy
1998
Several psycholinguistic studies have investigated the influence of local and global semantic contexts on word processing. The first aim of the present study was to examine local and global level contributions to harmonic priming. The second was to test a spreading-activation account of harmonic context effects (Bharucha, 1987). The expectations for the last chord (the target) of eight-chord sequences were varied by simultaneously manipulating the harmonic relationship of the target to the first six chords (global context) and to the seventh chord (local context). Human performances demonstrated that harmonic expectancies are derived from both the global and local levels of musical structur…
Genre-adaptive Semantic Computing and Audio-based Modelling for Music Mood Annotation
2016
This study investigates whether taking genre into account is beneficial for automatic music mood annotation in terms of core affects valence, arousal, and tension, as well as several other mood scales. Novel techniques employing genre-adaptive semantic computing and audio-based modelling are proposed. A technique called the ACTwg employs genre-adaptive semantic computing of mood-related social tags, whereas ACTwg-SLPwg combines semantic computing and audio-based modelling, both in a genre-adaptive manner. The proposed techniques are experimentally evaluated at predicting listener ratings related to a set of 600 popular music tracks spanning multiple genres. The results show that ACTwg outpe…
METALANG. Protocolo franco-español de exploración de habilidades metalingüísticas en niños de 6 a 9 años: un estudio preliminar
2012
International audience; In this work are described the principles of functional-pragmatic and the reasons for developing an exploration protocol for natural metalinguistic abilities. This study explains the base hypothesis and structure of METALANG protocol. This protocol consists in a Test and a Questionnaire for parents with two different scales: A = Ability, B = Frequency. Each element of the protocol has 6 sections and 40 items. It is performed a preliminary contrast with 12 subjects aged 6 to 9 years. Among the 12 subjects, 4 were diagnosed with dysphasia. METALANG shows high scores in reliability and internal consistency. This result confirms the hypothesis that it is possible a joint…
Inducing the Lyndon Array
2019
In this paper we propose a variant of the induced suffix sorting algorithm by Nong (TOIS, 2013) that computes simultaneously the Lyndon array and the suffix array of a text in $O(n)$ time using $\sigma + O(1)$ words of working space, where $n$ is the length of the text and $\sigma$ is the alphabet size. Our result improves the previous best space requirement for linear time computation of the Lyndon array. In fact, all the known linear algorithms for Lyndon array computation use suffix sorting as a preprocessing step and use $O(n)$ words of working space in addition to the Lyndon array and suffix array. Experimental results with real and synthetic datasets show that our algorithm is not onl…
Using Hankel matrices for dynamics-based facial emotion recognition and pain detection
2015
This paper proposes a new approach to model the temporal dynamics of a sequence of facial expressions. To this purpose, a sequence of Face Image Descriptors (FID) is regarded as the output of a Linear Time Invariant (LTI) system. The temporal dynamics of such sequence of descriptors are represented by means of a Hankel matrix. The paper presents different strategies to compute dynamics-based representation of a sequence of FID, and reports classification accuracy values of the proposed representations within different standard classification frameworks. The representations have been validated in two very challenging application domains: emotion recognition and pain detection. Experiments on…
ASR performance prediction on unseen broadcast programs using convolutional neural networks
2018
In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably …
Analyzing Learned Representations of a Deep ASR Performance Prediction Model
2018
This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate. This work is dedicated to the analysis of speech signal embeddings and text embeddings learnt by the CNN while training our prediction model. We try to better understand which information is captured by the deep model and its relation with different conditioning factors. It is shown that hidden layers convey a clear signal about speech style, accent and broadcast type. We then try to leverage these 3 types of information …
Towards the evaluation of automatic simultaneous speech translation from a communicative perspective
2021
In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine…
Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network
2020
In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use atten…
An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments
2020
The problem of training with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning (DL) algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. In the image domain, typical FSL applications include those related to face recognition. In the audio domain, music fraud or speaker recognition can be clearly benefited from FSL methods. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, usin…