Related papers: EESEN: End-to-End Speech Recognition using Deep RN…

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…

In recent years, deep neural networks (DNNs) were studied as an alternative to traditional acoustic echo cancellation (AEC) algorithms. The proposed models achieved remarkable performance for the separate tasks of AEC and residual echo…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency. One of the key ingredients is the…

Background. Previous state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text "feature engineering" and conventional machine learning algorithms such as conditional…

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the…

In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a…

The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature…

Deep neural networks (DNNs) have recently achieved great success in a multitude of classification tasks. Ensembles of DNNs have been shown to improve the performance. In this paper, we explore the recent state-of-the-art DNNs used for image…

Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…

As for the humanoid robots, the internal noise, which is generated by motors, fans and mechanical components when the robot is moving or shaking its body, severely degrades the performance of the speech recognition accuracy. In this paper,…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a…

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…

Previous research has looked into ways to improve speech emotion recognition (SER) by utilizing both acoustic and linguistic cues of speech. However, the potential association between state-of-the-art ASR models and the SER task has yet to…

Human speech contains both linguistic content and speaker dependent characteristics making speaker verification a key technology in identity critical applications. Modern deep learning speaker verification systems aim to learn speaker…

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. However,…

Recent achievements in end-to-end deep learning have encouraged the exploration of tasks dealing with highly structured data with unified deep network models. Having such models for compressing audio signals has been challenging since it…

Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…

Dense stereo matching with deep neural networks is of great interest to the research community. Existing stereo matching networks typically use slow and computationally expensive 3D convolutions to improve the performance, which is not…