相关论文: Robust and Efficient Autoregressive Speech Synthes…

Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work,…

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The…

Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone…

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

The unified autoregressive (AR) model excels at multimodal understanding and generation. However, its full potential in the domain of customized image generation has yet to be fully realized. Existing customization approaches for unified AR…

Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retrieval. While recent work explores asynchronous retrieval, existing approaches rely on…

Designing a universal policy architecture that performs well across diverse robots and task configurations remains a key challenge. In this work, we address this by representing robot actions as sequential data and generating actions…

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

This paper proposes a forward attention method for the sequenceto- sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the…

Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address…

This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant…

In this work, we propose a streaming speech recognition framework for Amdo Tibetan, built upon a hybrid CTC/Atten-tion architecture with a context-aware dynamic chunking mechanism. The proposed strategy adaptively adjusts chunk widths based…

Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from…

Attention based neural TTS is elegant speech synthesis pipeline and has shown a powerful ability to generate natural speech. However, it is still not robust enough to meet the stability requirements for industrial products. Besides, it…

Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs.…

Current state-of-the-art approaches for image captioning typically adopt an autoregressive manner, i.e., generating descriptions word by word, which suffers from slow decoding issue and becomes a bottleneck in real-time applications.…

Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yield greater efficiency. Yet, in practice, current open-source…

As an indispensable part of modern human-computer interaction system, speech synthesis technology helps users get the output of intelligent machine more easily and intuitively, thus has attracted more and more attention. Due to the…

Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While existing methods accelerate inference by pruning tokens using frequency maps, their binary…