Related papers: Segmental Recurrent Neural Networks for End-to-end…
We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length. To this end we propose a convolutional neural network (CNN) based architecture which…
Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learning the optimal feature map is often…
Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to…
In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the…
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum,via a naive convolution…
The field of speech recognition is in the midst of a paradigm shift: end-to-end neural networks are challenging the dominance of hidden Markov models as a core technology. Using an attention mechanism in a recurrent encoder-decoder…
In this paper we investigate continuous speech recognition using electroencephalography (EEG) features using recently introduced end-to-end transformer based automatic speech recognition (ASR) model. Our results demonstrate that transformer…
Deep learning approaches are still not very common in the speaker verification field. We investigate the possibility of using deep residual convolutional neural network with spectrograms as an input features in the text-dependent speaker…
This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs)…
Modern computer vision (CV) is often based on convolutional neural networks (CNNs) that excel at hierarchical feature extraction. The previous generation of CV approaches was often based on conditional random fields (CRFs) that excel at…
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…
Fine-grained action segmentation and recognition is an important yet challenging task. Given a long, untrimmed sequence of kinematic data, the task is to classify the action at each time frame and segment the time series into the correct…
This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding. It is trained to output letters, with transcribed speech, without the need for force…
Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…
This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…
Neural end-to-end (E2E) models have become a promising technique to realize practical automatic speech recognition (ASR) systems. When realizing such a system, one important issue is the segmentation of audio to deal with streaming input or…
Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS.…
This paper proposes a Region-based Convolutional Recurrent Neural Network (R-CRNN) for audio event detection (AED). The proposed network is inspired by Faster-RCNN, a well known region-based convolutional network framework for visual object…
Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling has shown additional improvements by training a spatial…
Discriminative segmental models, such as segmental conditional random fields (SCRFs) and segmental structured support vector machines (SSVMs), have had success in speech recognition via both lattice rescoring and first-pass decoding.…