相关论文: Streaming ResLSTM with Causal Mean Aggregation for…

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder…

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all…

A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with…

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the…

In recent years, distracted driving has garnered considerable attention as it continues to pose a significant threat to public safety on the roads. This has increased the need for innovative solutions that can identify and eliminate…

In many applications of multi-microphone multi-device processing, the synchronization among different input channels can be affected by the lack of a common clock and isolated drops of samples. In this work, we address the issue of sample…

In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards…

Predictive queries over spatiotemporal (ST) stream data pose significant data processing and analysis challenges. ST data streams involve a set of time series whose data distributions may vary in space and time, exhibiting multiple distinct…

Streaming automatic speech recognition (ASR) models are restricted from accessing future context, which results in worse performance compared to the non-streaming models. To improve the performance of streaming ASR, knowledge distillation…

We propose a streaming non-autoregressive (non-AR) decoding algorithm to deliberate the hypothesis alignment of a streaming RNN-T model. Our algorithm facilitates a simple greedy decoding procedure, and at the same time is capable of…

In this paper we develop an online statistical inference approach for high-dimensional generalized linear models with streaming data for real-time estimation and inference. We propose an online debiased lasso (ODL) method to accommodate the…

Most real-world datasets, and particularly those collected from physical systems, are full of noise, packet loss, and other imperfections. However, most specification mining, anomaly detection and other such algorithms assume, or even…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph recurrent network, which views words as nodes and performs layer-wise recurrent steps between them simultaneously. Despite its successes on text representations, the…

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

The present paper introduces a novel approach to studying social media habits through predictive modeling of sequential smartphone user behaviors. While much of the literature on media and technology habits has relied on self-report…

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during…

The Transducer (e.g. RNN-Transducer or Conformer-Transducer) generates an output label sequence as it traverses the input sequence. It is straightforward to use in streaming mode, where it generates partial hypotheses before the complete…

Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…