Related papers: A Streaming End-to-End Framework For Spoken Langua…
Natural language understanding (NLU) in the context of goal-oriented dialog systems typically includes intent classification and slot labeling tasks. Existing methods to expand an NLU system to new languages use machine translation with…
Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
In emotional support conversations, unclear intentions can lead supporters to employ inappropriate strategies, inadvertently imposing their expectations or solutions on the seeker. Clearly defined intentions are essential for guiding both…
Understanding human intent is a complex, high-level task for large language models (LLMs), requiring analytical reasoning, contextual interpretation, dynamic information aggregation, and decision-making under uncertainty. Real-world public…
Several end-to-end deep learning approaches have been recently presented which extract either audio or visual features from the input images or audio signals and perform speech recognition. However, research on end-to-end audiovisual models…
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…
In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information. Previous studies on Chinese SLU do not consider the word information, failing to detect word boundaries that are beneficial for intent…
Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…
End-to-end (E2E) spoken language understanding (SLU) systems avoid an intermediate textual representation by mapping speech directly into intents with slot values. This approach requires considerable domain-specific training data. In…
This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…
Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the…
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose a scalable and automatic…
Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…
New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems. Existing works towards NID mainly adopt a cascaded architecture, wherein the…
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or…
With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component…
Huge amounts of textual conversations occur online every day, where multiple conversations take place concurrently. Interleaved conversations lead to difficulties in not only following the ongoing discussions but also extracting relevant…
End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the…
Conversational systems have a Natural Language Understanding (NLU) module. In this module, there is a task known as an intent classification that aims at identifying what a user is attempting to achieve from an utterance. Previous works use…