Related papers: Discovering phoneme-specific critical articulators…

The growing prevalence of neurological disorders associated with dysarthria motivates the need for automated intelligibility assessment methods that are applicalbe across languages. However, most existing approaches are either limited to a…

Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages. However, a limitation is that a pronunciation lexicon…

In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data in two languages for…

Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and…

Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes…

Several approaches exist for the recording of articulatory movements, such as eletromagnetic and permanent magnetic articulagraphy, ultrasound tongue imaging and surface electromyography. Although magnetic resonance imaging (MRI) is more…

The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a…

In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be extracted efficiently with linear activation in the embedding layer. To understand…

We propose a novel reinforcement learning-based approach for adaptive and iterative feature selection. Given a masked vector of input features, a reinforcement learning agent iteratively selects certain features to be unmasked, and uses…

Speaker embeddings achieve promising results on many speaker verification tasks. Phonetic information, as an important component of speech, is rarely considered in the extraction of speaker embeddings. In this paper, we introduce phonetic…

Speech-driven 3D facial animation aims to generate realistic facial movements synchronized with audio. Traditional methods primarily minimize reconstruction loss by aligning each frame with ground-truth. However, this frame-wise approach…

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models…

Despite the increasing research interest in end-to-end learning systems for speech emotion recognition, conventional systems either suffer from the overfitting due in part to the limited training data, or do not explicitly consider the…

Wake word detection exists in most intelligent homes and portable devices. It offers these devices the ability to "wake up" when summoned at a low cost of power and computing. This paper focuses on understanding alignment's role in…

Acoustic-to-articulatory inversion (AAI) is to convert audio into articulator movements, such as ultrasound tongue imaging (UTI) data. An issue of existing AAI methods is only using the personalized acoustic information to derive the…

This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…

Weight averaging of Stochastic Gradient Descent (SGD) iterates is a popular method for training deep learning models. While it is often used as part of complex training pipelines to improve generalization or serve as a `teacher' model,…

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…

Error correcting codes play a central role in digital communication, ensuring that transmitted information can be accurately reconstructed despite channel impairments. Recently, autoencoder (AE) based approaches have gained attention for…