相关论文: Speech-Text Dialog Pre-training for Spoken Dialog …

Recent studies have demonstrated that prompting large language models (LLM) with audio encodings enables effective speech recognition capabilities. However, the ability of Speech LLMs to comprehend and process multi-channel audio with…

Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e.g., vision, text. How to design a unified framework to integrate…

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various…

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

Pre-trained language models (PTLM) have achieved impressive results in a range of natural language understanding (NLU) and generation (NLG) tasks. However, current pre-training objectives such as masked token prediction (for BERT-style…

Large pretrained language models have been performing increasingly well in a variety of downstream tasks via prompting. However, it remains unclear from where the model learns the task-specific knowledge, especially in a zero-shot setup. In…

In spoken conversational question answering (SCQA), the answer to the corresponding question is generated by retrieving and then analyzing a fixed spoken document, including multi-part conversations. Most SCQA systems have considered only…

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM),…

We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5, enables simple, end-to-end transformer based models to outperform pipelined neural architectures…

One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Since data collection for machine learning models for this task is…

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations…

End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current…

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an…

A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach…

This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub "prompt-based learning". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output…