相关论文: SqueezeWave: Extremely Lightweight Vocoders for On…

Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech…

We propose StyleTalker, a novel audio-driven talking head generation model that can synthesize a video of a talking person from a single reference image with accurately audio-synced lip shapes, realistic head poses, and eye blinks.…

Recent breakthroughs in zero-shot voice synthesis have enabled imitating a speaker's voice using just a few seconds of recording while maintaining a high level of realism. Alongside its potential benefits, this powerful technology…

Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and…

Voice controlled devices and services have become very popular in the consumer IoT. Cloud-based speech analysis services extract information from voice inputs using speech recognition techniques. Services providers can thus build very…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount…

Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over…

Recent advances in text-to-speech (TTS) synthesis, such as Tacotron and WaveRNN, have made it possible to construct a fully neural network based TTS system, by coupling the two components together. Such a system is conceptually simple as it…

In recent years, several text-to-speech systems have been proposed to synthesize natural speech in zero-shot, few-shot, and low-resource scenarios. However, these methods typically require training with data from many different speakers.…

Lenses that can collect the perfect image of an object must restore propagative and evanescent waves. However, for efficient information transfer, e.g., in compressed sensing, it is often desirable to detect only the fast spatial variations…

The pre-trained speech encoder wav2vec 2.0 performs very well on various spoken language understanding (SLU) tasks. However, on many tasks, it trails behind text encoders with textual input. To improve the understanding capability of SLU…

The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference process, while their…

This paper proposes a novel way of doing audio synthesis at the waveform level using Transformer architectures. We propose a deep neural network for generating waveforms, similar to wavenet. This is fully probabilistic, auto-regressive, and…

Expressive speech synthesis models are trained by adding corpora with diverse speakers, various emotions, and different speaking styles to the dataset, in order to control various characteristics of speech and generate the desired voice. In…

Existing 3D visual grounding methods rely on precise text prompts to locate objects within 3D scenes. Speech, as a natural and intuitive modality, offers a promising alternative. Real-world speech inputs, however, often suffer from…

Sound is an essential sensing element for many organisms in nature, and multiple species have evolved organic structures that create complex acoustic scattering and dispersion phenomena to emit and perceive sound unambiguously. To date, it…

Prevailing Video-to-Audio (V2A) generation models operate offline, assuming an entire video sequence or chunks of frames are available beforehand. This critically limits their use in interactive applications such as live content creation…

A large part of the expressive speech synthesis literature focuses on learning prosodic representations of the speech signal which are then modeled by a prior distribution during inference. In this paper, we compare different prior…

From radio-electronics signal analysis to biological samples actuation, surface acoustic waves (SAW) are involved in a multitude of modern devices. Despite this versatility, SAW transducers developed up to date only authorize the synthesis…