Related papers: BridgeNets: Student-Teacher Transfer Learning Base…

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…

Transfer learning has become the de facto standard in computer vision and natural language processing, especially where labeled data is scarce. Accuracy can be significantly improved by using pre-trained models and subsequent fine-tuning.…

In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English ASR model and show that transfer learning can be effectively…

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks. Most existing approaches use expert-defined rules or rule-based features to directly approach this task, but these…

We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an…

Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not…

Continual learning aims to create artificial neural networks capable of accumulating knowledge and skills through incremental training on a sequence of tasks. The main challenge of continual learning is catastrophic interference, wherein…

Deep learning empirically achieves high performance in many applications, but its training dynamics has not been fully understood theoretically. In this paper, we explore theoretical analysis on training two-layer ReLU neural networks in a…

A deep learning approach has been proposed recently to derive speaker identifies (d-vector) by a deep neural network (DNN). This approach has been applied to text-dependent speaker recognition tasks and shows reasonable performance gains…

In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this…

Diffusion, a fundamental internal mechanism emerging in many physical processes, describes the interaction among different objects. In many learning tasks with limited training samples, the diffusion connects the labeled and unlabeled data…

Deep learning and knowledge transfer techniques have permeated the field of medical imaging and are considered as key approaches for revolutionizing diagnostic imaging practices. However, there are still challenges for the successful…

Extracting the speech of a target speaker from mixed audios, based on a reference speech from the target speaker, is a challenging yet powerful technology in speech processing. Recent studies of speaker-independent speech separation, such…

Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term…

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address…

Almost half a billion people world-wide suffer from disabling hearing loss. While hearing aids can partially compensate for this, a large proportion of users struggle to understand speech in situations with background noise. Here, we…

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

Dialogue response selection is an important part of Task-oriented Dialogue Systems (TDSs); it aims to predict an appropriate response given a dialogue context. Obtaining key information from a complex, long dialogue context is challenging,…