相关论文: Multi-view Frequency LSTM: An Efficient Frontend f…

In visual speech processing, context modeling capability is one of the most important requirements due to the ambiguous nature of lip movements. For example, homophenes, words that share identical lip movements but produce different sounds,…

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Recent advances show that large language models (LLMs) generalize strong performance across different natural language benchmarks. However, the large size of LLMs makes training and inference expensive and impractical to run in…

The disparity in phonology between learner's native (L1) and target (L2) language poses a significant challenge for mispronunciation detection and diagnosis (MDD) systems. This challenge is further intensified by lack of annotated L2 data.…

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

We introduce and explore a new multimodal input representation for vision-language models: acoustic field video. Unlike conventional video (RGB with stereo/mono audio), our video stream provides a spatially grounded visualization of sound…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Modern wake word detection systems usually rely on neural networks for acoustic modeling. Transformers has recently shown superior performance over LSTM and convolutional networks in various sequence modeling tasks with their better…

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse…

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…

In this paper, we propose BeamLLM, a vision-aided millimeter-wave (mmWave) beam prediction framework leveraging large language models (LLMs) to address the challenges of high training overhead and latency in mmWave communication systems. By…

As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance efficiency and quality, we introduce LLMSteer, a…

We present a novel model designed for resource-efficient multichannel speech enhancement in the time domain, with a focus on low latency, lightweight, and low computational requirements. The proposed model incorporates explicit spatial and…

Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual…

Interactions with virtual assistants typically start with a trigger phrase followed by a command. In this work, we explore the possibility of making these interactions more natural by eliminating the need for a trigger phrase. Our goal is…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

We propose and analyze the use of an explicit time-context window for neural network-based spectral masking speech enhancement to leverage signal context dependencies between neighboring frames. In particular, we concentrate on soft masking…

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features…

For many small- and medium-vocabulary tasks, audio-visual speech recognition can significantly improve the recognition rates compared to audio-only systems. However, there is still an ongoing debate regarding the best combination strategy…