相关论文: DualSpec: Text-to-spatial-audio Generation via Dua…

We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable…

This paper explores the instruction fine-tuning technique for speech-to-semantic tasks by introducing a unified end-to-end (E2E) framework that generates target text conditioned on a task-related prompt for audio data. We pre-train the…

The content of visual and audio scenes is multi-faceted such that a video can be paired with various audio and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the…

This paper proposes a method for selecting training data for text-to-speech (TTS) synthesis from dark data. TTS models are typically trained on high-quality speech corpora that cost much time and money for data collection, which makes it…

In recent years, text-to-audio systems have achieved remarkable success, enabling the generation of complete audio segments directly from text descriptions. While these systems also facilitate music creation, the element of human creativity…

Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large…

This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely.…

We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained with minimal supervision. By combining two types of discrete speech representations, we cast TTS as a composition of two sequence-to-sequence tasks:…

Binaural audio generation (BAG) aims to convert monaural audio to stereo audio using visual prompts, requiring a deep understanding of spatial and semantic information. However, current models risk overfitting to room environments and lose…

This study investigates whether phonological features can be applied in text-to-speech systems to generate native and non-native speech in English and Mandarin. We present a mapping of ARPABET/pinyin to SAMPA/SAMPA-SC and then to…

Audio-driven video generation aims to synthesize realistic videos that align with input audio recordings, akin to the human ability to visualize scenes from auditory input. However, existing approaches predominantly focus on exploring…

Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions. How to effectively leverage bidirectional supervision signals to produce high-fidelity audio for both directions? Existing…

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates…

Over the past decade, a series of unflagging efforts have been dedicated to developing highly expressive and controllable text-to-speech (TTS) systems. In general, the holistic TTS comprises two interconnected components: the frontend…

Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming…

In recent years, the burgeoning interest in diffusion models has led to significant advances in image and speech generation. Nevertheless, the direct synthesis of music waveforms from unrestricted textual prompts remains a relatively…

Diffusion based Text-To-Music (TTM) models generate music corresponding to text descriptions. Typically UNet based diffusion models condition on text embeddings generated from a pre-trained large language model or from a cross-modality…

Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of…

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…

Diffusion-based text-to-audio (TTA) generation has made substantial progress, leveraging latent diffusion model (LDM) to produce high-quality, diverse and instruction-relevant audios. However, beyond generation, the task of audio editing…