Related papers: Evolutionary Algorithm Enhanced Neural Architectur…
The ongoing advancements in network architecture design have led to remarkable achievements in deep learning across various challenging computer vision tasks. Meanwhile, the development of neural architecture search (NAS) has provided…
The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims at automatically designing neural network architectures in…
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…
This paper introduces Evolutionary Multi-Objective Network Architecture Search (EMNAS) for the first time to optimize neural network architectures in large-scale Reinforcement Learning (RL) for Autonomous Driving (AD). EMNAS uses genetic…
The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive;…
We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the…
Cognitive diagnosis plays a vital role in modern intelligent education platforms to reveal students' proficiency in knowledge concepts for subsequent adaptive tasks. However, due to the requirement of high model interpretability, existing…
Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…
Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained…
Background noise is a well-known factor that deteriorates the accuracy and reliability of speaker verification (SV) systems by blurring speech intelligibility. Various studies have used separate pretrained enhancement models as the…
By the widespread popularity of electronic devices, the emergence of biometric technology has brought significant convenience to user authentication compared with the traditional password and mode unlocking. Among many biological…
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy…
The classical i-vectors and the latest end-to-end deep speaker embeddings are the two representative categories of utterance-level representations in automatic speaker verification systems. Traditionally, once i-vectors or deep speaker…
As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique missing from incremental…
In this work, we continue in our research on i-vector extractor for speaker verification (SV) and we optimize its architecture for fast and effective discriminative training. We were motivated by computational and memory requirements caused…
Automated speaker recognition uses data processing to identify speakers by their voice. Today, automated speaker recognition is deployed on billions of smart devices and in services such as call centres. Despite their wide-scale deployment…
To achieve excellent performance with modern neural networks, having the right network architecture is important. Neural Architecture Search (NAS) concerns the automatic discovery of task-specific network architectures. Modern NAS…
We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and…
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation. The underlying idea for the…
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is…