相关论文: Zipper: A Multi-Tower Decoder Architecture for Fus…

Multimodal headline utilizes both video frames and transcripts to generate the natural language title of the videos. Due to a lack of large-scale, manually annotated data, the task of annotating grounded headlines for video is labor…

The focus of this paper is on the analysis and design of Raptor codes using a multi-edge framework. In this regard, we first represent the Raptor code as a multi-edge type low-density parity-check (METLDPC) code. This MET representation…

Transformer-based text to speech (TTS) model (e.g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e.g.,…

We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task,…

Next-generation wireless networks are expected to leverage multi-modal data sources to execute various wireless communication tasks such as beamforming and blockage prediction with situational-awareness. To do so, multi-modal transformers…

Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat these abilities in isolation, such that tasks with multimodal…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

This paper investigates the inverse capabilities and broader utility of multimodal latent spaces within task-specific AI (Artificial Intelligence) models. While these models excel at their designed forward tasks (e.g., text-to-image…

This paper presents Z-Code++, a new pre-trained language model optimized for abstractive text summarization. The model extends the state of the art encoder-decoder model using three techniques. First, we use a two-phase pre-training process…

We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…

Diffusion models have demonstrated significant potential in achieving state-of-the-art performance across various text generation tasks. In this systematic study, we investigate their application to the table-to-text problem by adapting the…

Audio-driven 3D facial animation aims to map input audio to realistic facial motion. Despite significant progress, limitations arise from inconsistent 3D annotations, restricting previous models to training on specific annotations and…

We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix…

This paper proposes a novel technique to obtain better downstream ASR performance from a joint encoder-decoder self-supervised model when trained with speech pooled from two different channels (narrow and wide band). The joint…

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

While there have been significant advances in de-tecting emotions in text, in the field of utter-ance-level emotion recognition (ULER), there are still many problems to be solved. In this paper, we address some challenges in ULER in dialog…

Emotion recognition is inherently ambiguous, with uncertainty arising both from rater disagreement and from discrepancies across modalities such as speech and text. There is growing interest in modeling rater ambiguity using label…

Training on multiple modalities of input can augment the capabilities of a language model. Here, we ask whether such a training regime can improve the quality and efficiency of these systems as well. We focus on text--audio and introduce…

Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing…

Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The…