Related papers: AFD-SLU: Adaptive Feature Distillation for Spoken …

Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between…

Recently, Large language models (LLMs) with in-context learning have demonstrated remarkable potential in handling neural machine translation. However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply…

Recent voice assistants are usually based on the cascade spoken language understanding (SLU) solution, which consists of an automatic speech recognition (ASR) engine and a natural language understanding (NLU) system. Because such approach…

Multi-Intent Spoken Language Understanding (SLU), a novel and more complex scenario of SLU, is attracting increasing attention. Unlike traditional SLU, each intent in this scenario has its specific scope. Semantic information outside the…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Performance of spoken language understanding (SLU) can be degraded with automatic speech recognition (ASR) errors. We propose a novel approach to improve SLU robustness by randomly corrupting clean training text with an ASR error simulator,…

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure…

Deep learning models have achieved significant results across various computer vision tasks. However, due to the large number of parameters in these models, deploying them in real-time scenarios is a critical challenge, specifically in…

Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference introduced during multimodal adaptation. Such loss is…

Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally…

Intent detection and slot filling are two main tasks in natural language understanding (NLU) for identifying users' needs from their utterances. These two tasks are highly related and often trained jointly. However, most previous works…

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…

When a human communicates with a machine using natural language on the web and online, how can it understand the human's intention and semantic context of their talk? This is an important AI task as it enables the machine to construct a…

Intent Recognition and Slot Identification are crucial components in spoken language understanding (SLU) systems. In this paper, we present a novel approach towards both these tasks in the context of low resourced and unwritten languages.…

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…

Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…

Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly…

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…