Sorry, you need to enable JavaScript to visit this website.

In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for contextualizing speech recognition models incorporating LLMs. Our approach casts speech recognition as a mixed-modal language modeling task based on a pretrained LLM. We provide audio features, along with optional text tokens for context, to train the system to complete transcriptions in a decoderonly fashion.

Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods. These models transform clean speech training samples into Gaussian noise, usually centered on noisy speech, and subsequently learn a parameterized

Inference of time-varying data over graphs is of importance in real-world applications such as urban water networks, economics, and brain recordings. It typically relies on identifying a computationally affordable joint spatiotemporal method that can leverage the patterns in the data. While this per se is a challenging task, it becomes even more so when the network comes with uncertainties, which, if not accounted for, can lead to unpredictable consequences.

In recent work [1], we developed a distributed stochastic multi-arm contextual bandit algorithm to learn optimal actions when the contexts are unknown, and M agents work collaboratively under the coordination of a central server to minimize the total regret. In our model, the agents observe only the context distribution and the exact context is unknown to the agents. Such a situation arises, for instance, when the context itself is a noisy measurement or based on a prediction mechanism.

In contrast to existing multi-band Wi-Fi fusion in a frame-to-frame basis for simple classification, this paper considers asynchronous sequence-to-sequence fusion between sub-7GHz channel state information (CSI) and 60GHz beam SNR for more challenging downstream tasks such as continuous regression.

In recent work [1], we developed a distributed stochastic multi-arm contextual bandit algorithm to learn optimal actions when the contexts are unknown, and M agents work collaboratively under the coordination of a central server to minimize the total regret. In our model, the agents observe only the context distribution and the exact context is unknown to the agents. Such a situation arises, for instance, when the context itself is a noisy measurement or based on a prediction mechanism.

High-quality speech synthesis models may be used to spread misinformation or impersonate voices. Audio watermarking can help combat such misuses by embedding a traceable signature in generated audio. However, existing audio watermarks are not designed for synthetic speech and typically demonstrate robustness to only a small set of transformations of the watermarked audio. To address this, we propose MaskMark, a neural network-based digital audio watermarking technique optimized for speech.

A speech emotion recognition (SER) system deployed on a real-world application can encounter speech contaminated with unconstrained background noise. To deal with this issue,

Although deep learning (DL) based end-to-end models have shown outstanding performance in multi-channel speech extraction, their practical applications on edge devices are restricted due to their high computational complexity. In this paper, we propose a hybrid system that can more effectively integrate the generalized sidelobe canceller (GSC) and a lightweight post-filtering model under the assistance of spatial speaker activity information provided by a directional voice activity detection (DVAD) module.

This paper proposes two novel variants of neural reprogramming to enhance wake word recognition in streaming end-to-end ASR models without updating model weights. The first, "trigger-frame reprogramming", prepends the input speech feature sequence with the learned trigger-frames of the target wake word to adjust ASR model’s hidden states for improved wake word recognition. The second, "predictor-state initialization", trains only the initial state vectors (cell and hidden states) of the LSTMs in the prediction network.