相关论文: Tensor-Train Long Short-Term Memory for Monaural S…

State-of-the-art forecasting methods using Recurrent Neural Net- works (RNN) based on Long-Short Term Memory (LSTM) cells have shown exceptional performance targeting short-horizon forecasts, e.g given a set of predictor features, forecast…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

The standard LSTM, although it succeeds in the modeling long-range dependences, suffers from a highly complex structure that can be simplified through modifications to its gate units. This paper was to perform an empirical comparison…

This work aims to design a low complexity spoken command recognition (SCR) system by considering different trade-offs between the number of model parameters and classification accuracy. More specifically, we exploit a deep hybrid…

Analysis of time-series data allows to identify long-term trends and make predictions that can help to improve our lives. With the rapid development of artificial neural networks, long short-term memory (LSTM) recurrent neural network (RNN)…

Recent developments in speech synthesis have produced systems capable of outcome intelligible speech, but now researchers strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple…

Model compression is significant for the wide adoption of Recurrent Neural Networks (RNNs) in both user devices possessing limited resources and business clusters requiring quick responses to large-scale service requests. This work aims to…

This paper introduces Grid Long Short-Term Memory, a network of LSTM cells arranged in a multidimensional grid that can be applied to vectors, sequences or higher dimensional data such as images. The network differs from existing deep LSTM…

Longlshort-term memory (LSTM) is a deep learning model that can capture long-term dependencies of wireless channel models and is highly adaptable to short-term changes in a wireless environment. This paper proposes a simple LSTM model to…

Most of the deep learning based speech enhancement (SE) methods rely on estimating the magnitude spectrum of the clean speech signal from the observed noisy speech signal, either by magnitude spectral masking or regression. These methods…

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly…

Recently, tensor data (or multidimensional array) have been generated in many modern applications, such as functional magnetic resonance imaging (fMRI) in neuroscience and videos in video analysis. Many efforts are made in recent years to…

Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling. It aims to use gates to control information flow (e.g., whether to skip some information or not) in the recurrent computations, although…

Deep learning has shown a great potential for speech separation, especially for speech and non-speech separation. However, it encounters permutation problem for multi-speaker separation where both target and interference are speech.…

In this work, we firstly apply the Train-Tensor (TT) networks to construct a compact representation of the classical Multilayer Perceptron, representing a reduction of up to 95% of the coefficients. A comparative analysis between tensor…

Recursive neural networks (RNN) and their recently proposed extension recursive long short term memory networks (RLSTM) are models that compute representations for sentences, by recursively combining word embeddings according to an…

Recently, machine learning methods have provided a broad spectrum of original and efficient algorithms based on Deep Neural Networks (DNN) to automatically predict an outcome with respect to a sequence of inputs. Recurrent hidden cells…

Large language models (LLMs) are both storage-intensive and computation-intensive, posing significant challenges when deployed on resource-constrained hardware. As linear layers in LLMs are mainly resource consuming parts, this paper…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…