Related papers: CNN Encoding of Acoustic Parameters for Prominence…

Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural…

Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…

The detection of pathologies from speech features is usually defined as a binary classification task with one class representing a specific pathology and the other class representing healthy speech. In this work, we train neural networks,…

Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand…

This paper presents an alternate representation framework to commonly used time-frequency representation for acoustic scene classification (ASC). A raw audio signal is represented using a pre-trained convolutional neural network (CNN) using…

Level assessment for foreign language students is necessary for putting them in the right level group, furthermore, interviewing students is a very time-consuming task, so we propose to automate the evaluation of speaker fluency level by…

Current automatic depression detection systems provide predictions directly without relying on the individual symptoms/items of depression as denoted in the clinical depression rating scales. In contrast, clinicians assess each item in the…

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

We present CONSENT, a simple yet effective CONtext SENsitive Transformer framework for context-dependent object classification within a fully-trainable end-to-end deep learning pipeline. We exemplify the proposed framework on the task of…

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…

Computational research on error detection in second language speakers has mainly addressed clear grammatical anomalies typical to learners at the beginner-to-intermediate level. We focus instead on acquisition of subtle semantic nuances of…

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical…

Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and…

Repeated reading (RR) helps learners, who have little to no experience with reading fluently to gain confidence, speed and process words automatically. The benefits of repeated readings include helping all learners with fact recall, aiding…

Emotions lie on a continuum, but current models treat emotions as a finite valued discrete variable. This representation does not capture the diversity in the expression of emotion. To better represent emotions we propose the use of natural…

A major advantage of a deep convolutional neural network (CNN) is that the focused receptive field size is increased by stacking multiple convolutional layers. Accordingly, the model can explore the long-range dependency of features from…

Sentence classification is one of the basic tasks of natural language processing. Convolution neural network (CNN) has the ability to extract n-grams features through convolutional filters and capture local correlations between consecutive…

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models.…

Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric. Since such a labor-intensive approach is not feasible for large-scale speech quality…