Related papers: Towards multi-task learning of speech and speaker …

This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level…

Spoofing attacks posed by generating artificial speech can severely degrade the performance of a speaker verification system. Recently, many anti-spoofing countermeasures have been proposed for detecting varying types of attacks from…

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, and secure communications. Consequently, it will become a key enabler with the emerging fifth-generation (5G) and beyond 5G…

We consider a distributed multi-task learning scheme that accounts for multiple linear model estimation tasks with heterogeneous and/or correlated data streams. We assume that nodes can be partitioned into groups corresponding to different…

We introduce a technique for augmenting neural text-to-speech (TTS) with lowdimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-ofthe-art…

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex…

In this work, we introduce metric learning (ML) to enhance the deep embedding learning for text-independent speaker verification (SV). Specifically, the deep speaker embedding network is trained with conventional cross entropy loss and…

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings…

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…

Neural speaker embeddings trained using classification objectives have demonstrated state-of-the-art performance in multiple applications. Typically, such embeddings are trained on an out-of-domain corpus on a single task e.g., speaker…

In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of…

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…

With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate…

Automatic evaluating the performance of Open-domain dialogue system is a challenging problem. Recent work in neural network-based metrics has shown promising opportunities for automatic dialogue evaluation. However, existing methods mainly…

Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these…

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly…

Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are commonly used for such speaker adaptation, they require computationally expensive retraining for…