相关论文: Stabilising and accelerating light gated recurrent…

In this work, we investigate application of generative speech enhancement to improve the robustness of ASR models in noisy and reverberant conditions. We employ a recently-proposed speech enhancement model based on Schr\"odinger bridge,…

Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, their empirical…

The proliferation of deep neural networks has spawned the rapid development of acoustic echo cancellation and noise suppression, and plenty of prior arts have been proposed, which yield promising performance. Nevertheless, they rarely…

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant…

Visual cues, like lip motion, have been shown to improve the performance of Automatic Speech Recognition (ASR) systems in noisy environments. We propose LipGER (Lip Motion aided Generative Error Correction), a novel framework for leveraging…

Real-time emotion recognition (RTER) in conversations is significant for developing emotionally intelligent chatting machines. Without the future context in RTER, it becomes critical to build the memory bank carefully for capturing…

Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open challenge. Current…

This paper introduces GRAD, a real-time anomaly detection method for autonomous vehicle sensors that integrates statistical analysis and deep learning to ensure the reliability of sensor data. The proposed approach combines the Reinforced…

Audio captioning is a recently proposed task for automatically generating a textual description of a given audio clip. In this study, a novel deep network architecture with audio embeddings is presented to predict audio captions. Within the…

Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…

LSTMs are powerful tools for modeling contextual information, as evidenced by their success at the task of language modeling. However, modeling contexts in very high dimensional space can lead to poor generalizability. We introduce the…

Biological neural networks are capable of recruiting different sets of neurons to encode different memories. However, when training artificial neural networks on a set of tasks, typically, no mechanism is employed for selectively producing…

Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critical systems demands more than predictive accuracy. Standard…

Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input…

Recurrent neural networks (RNNs) have been a long-standing candidate for processing of temporal sequence data, especially in memory-constrained systems that one may find in embedded edge computing environments. Recent advances in training…

With the continuous growth of neural network scales, low-precision quantization is widely used in edge accelerators. Classic multi-threshold activation hardware requires 2^n thresholds for n-bit outputs, causing a rapid increase in hardware…

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the…

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…

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…

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them…