Related papers: Time-Frequency Localization Using Deep Convolution…
There exist several data-driven approaches that enable us model time series data including traditional regression-based modeling approaches (i.e., ARIMA). Recently, deep learning techniques have been introduced and explored in the context…
For speech recognition, deep neural networks (DNNs) have significantly improved the recognition accuracy in most of benchmark datasets and application domains. However, compared to the conventional Gaussian mixture models, DNN-based…
Convolutional neural networks (CNN) are one of the best-performing neural network architectures for environmental sound classification (ESC). Recently, temporal attention mechanisms have been used in CNN to capture the useful information…
A deep neural network (DNN)-based model has been developed to predict non-parametric distributions of durations of phonemes in specified phonetic contexts and used to explore which factors influence durations most. Major factors in US…
Continuous Sign Language Recognition (CSLR) is a challenging research task due to the lack of accurate annotation on the temporal sequence of sign language data. The recent popular usage is a hybrid model based on "CNN + RNN" for CSLR.…
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…
This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…
This paper is an extension of our previous conference paper. In recent years, there has been a growing interest among researchers in developing and improving speech recognition systems to facilitate and enhance human-computer interaction.…
This paper describes the extension and optimization of our previous work on very deep convolutional neural networks (CNNs) for effective recognition of noisy speech in the Aurora 4 task. The appropriate number of convolutional layers, the…
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantization techniques provides a powerful solution to dramatically…
Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This…
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…
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…
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.…
This study presents a systematic evaluation of time-frequency feature design for binaural sound source localization (SSL), focusing on how feature selection influences model performance across diverse conditions. We investigate the…
This study proposes a fully convolutional network (FCN) model for raw waveform-based speech enhancement. The proposed system performs speech enhancement in an end-to-end (i.e., waveform-in and waveform-out) manner, which dif-fers from most…
Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but…
Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video…
Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in real-valued models,…
Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the Time-Frequency Attention Cache Memory (TFACM) model, which…