Related papers: Amortized Neural Networks for Low-Latency Speech R…

We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Our architecture creates sparse computation pathways…

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. The architecture enables a dynamic pivot for its runtime…

Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation model, inverse text…

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming…

Recently, recurrent neural network transducer (RNN-T) gains increasing popularity due to its natural streaming capability as well as superior performance. Nevertheless, RNN-T training requires large time and computation resources as RNN-T…

The RNN-Transducer (RNN-T) framework for speech recognition has been growing in popularity, particularly for deployed real-time ASR systems, because it combines high accuracy with naturally streaming recognition. One of the drawbacks of…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and propose the latency-controlled NAS for acoustic modeling.…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal…

Recently, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) based models have been introduced to deep learning-based target speaker separation. In this paper, we propose an Attention-based neural network (Atss-Net) in the…

ATM-Net is a novel neural network architecture tailored for energy-harvested IoT devices, integrating adaptive termination points with multi-precision computing. It dynamically adjusts computational precision (32/8/4-bit) and network depth…

This paper presents AMNet, an Acoustic Model Network designed to improve the performance of Mandarin speech synthesis by incorporating phrase structure annotation and local convolution modules. AMNet builds upon the FastSpeech 2…

In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different…

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past…

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use…

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Neural network architectures are at the core of powerful automatic speech recognition systems (ASR). However, while recent researches focus on novel model architectures, the acoustic input features remain almost unchanged. Traditional ASR…

In this paper, a new deep learning architecture for stereo disparity estimation is proposed. The proposed atrous multiscale network (AMNet) adopts an efficient feature extractor with depthwise-separable convolutions and an extended cost…