Related papers: Generative Multi-modal Feedback for Singing Voice …

Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is…

Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and…

Conversational generative vision models (CGVMs) like Visual ChatGPT (Wu et al., 2023) have recently emerged from the synthesis of computer vision and natural language processing techniques. These models enable more natural and interactive…

Retrieval-augmented systems are typically evaluated in settings where information required to answer the query can be found within a single source or the answer is short-form or factoid-based. However, many real-world applications demand…

Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding explicit external control. In contrast, generative models are…

Multimodal language generation, which leverages the synergy of language and vision, is a rapidly expanding field. However, existing vision-language models face challenges in tasks that require complex linguistic understanding. To address…

This paper proposes a speech synthesis system that allows users to specify and control the acoustic characteristics of a speaker by means of prompts describing the speaker's traits of synthesized speech. Unlike previous approaches, our…

Textual style expresses a diverse set of information, including interpersonal dynamics (e.g., formality) and the author's emotions or attitudes (e.g., disgust). An open question is how language models can be explicitly controlled so that…

This paper proposes a novel framework for generating lingual descriptions of indoor scenes. Whereas substantial efforts have been made to tackle this problem, previous approaches focusing primarily on generating a single sentence for each…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre.…

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier models remains a fundamental challenge. Existing benchmarks…

Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key…

This paper proposes a generative moment matching network (GMMN)-based post-filter that provides inter-utterance pitch variation for deep neural network (DNN)-based singing voice synthesis. The natural pitch variation of a human singing…

Currently, many multi-speaker speech synthesis and voice conversion systems address speaker variations with an embedding vector. Modeling it directly allows new voices outside of training data to be synthesized. GMM based approaches such as…

In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…

Text-to-song (TTSong) is a music generation task that synthesizes accompanied singing voices. Current TTSong methods, inherited from singing voice synthesis (SVS), require melody-related information that can sometimes be impractical, such…

Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently…

With the similarity between music and speech synthesis from symbolic input and the rapid development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve the MIDI-to-audio performance by borrowing from TTS…