Related papers: V2C: Visual Voice Cloning
Vision-guided speech generation aims to produce authentic speech from facial appearance or lip motions without relying on auditory signals, offering significant potential for applications such as dubbing in filmmaking and assisting…
Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds…
Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have…
Videos, images, and sentences are mediums that can express the same semantics. One can imagine a picture by reading a sentence or can describe a scene with some words. However, even small changes in a sentence can cause a significant…
Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…
The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are…
Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of…
The adoption of voice assistants like Alexa or Siri has grown rapidly, allowing users to instantly access information via voice search. Query suggestion is a standard feature of screen-based search experiences, allowing users to explore…
This brief literature review studies the problem of audiovisual speech synthesis, which is the problem of generating an animated talking head given a text as input. Due to the high complexity of this problem, we approach it as the…
Modern voice cloning, also known as zero-shot text-to-speech (TTS), can synthesize speech that closely matches a target speaker from only seconds of reference audio, enabling applications such as personalized speech interfaces and dubbing.…
The goal of voice conversion (VC) is to convert input voice to match the target speaker's voice while keeping text and prosody intact. VC is usually used in entertainment and speaking-aid systems, as well as applied for speech data…
We introduce a novel speech synthesis system, called NAUTILUS, that can generate speech with a target voice either from a text input or a reference utterance of an arbitrary source speaker. By using a multi-speaker speech corpus to train…
Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features, which has attracted considerable attention from both natural language processing and computer vision communities. Currently, most comics…
Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine…
Voice faking, driven primarily by recent advances in text-to-speech (TTS) synthesis technology, poses significant societal challenges. Currently, the prevailing assumption is that unaltered human speech can be considered genuine, while fake…
This paper proposes a new voice conversion (VC) task from human speech to dog-like speech while preserving linguistic information as an example of human to non-human creature voice conversion (H2NH-VC) tasks. Although most VC studies deal…
Automatic movie narration aims to generate video-aligned plot descriptions to assist visually impaired audiences. Unlike standard video captioning, it involves not only describing key visual details but also inferring plots that unfold…
Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic…
This paper proposes visual-text to speech (vTTS), a method for synthesizing speech from visual text (i.e., text as an image). Conventional TTS converts phonemes or characters into discrete symbols and synthesizes a speech waveform from…
Audio captioning aims to generate text descriptions of audio clips. In the real world, many objects produce similar sounds. How to accurately recognize ambiguous sounds is a major challenge for audio captioning. In this work, inspired by…