Related papers: STCTS: Generative Semantic Compression for Ultra-L…
Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic deviations caused by generative hallucinations at ultra-low bitrate (bpp < 0.05), limiting its reliable deployment in…
Prosody is essential for speech technology, shaping comprehension, naturalness, and expressiveness. However, current text-to-speech (TTS) systems still struggle to accurately capture human-like prosodic variation, in part because existing…
Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…
Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…
The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It…
Semantic communication is a promising technology to improve communication efficiency by transmitting only the semantic information of the source data. However, traditional semantic communication methods primarily focus on data…
In this paper, we propose a robust semantic communication system for speech transmission, named Ross-S2T, by delivering the essential semantic information. Specifically, we consider the speech-to-text translation (S2TT) as the transmission…
Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct…
The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex…
Traditional text-to-speech (TTS) methods primarily focus on establishing a mapping between phonemes and mel-spectrograms. However, during the phoneme encoding stage, there is often a lack of real mel-spectrogram auxiliary information, which…
We present a neural text-to-speech (TTS) method that models natural vocal effort variation to improve the intelligibility of synthetic speech in the presence of noise. The method consists of first measuring the spectral tilt of unlabeled…
Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking in order to achieve human-like communication is the dynamic…
Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks…
Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into…
Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving…
Phonetic speech transcription is crucial for fine-grained linguistic analysis and downstream speech applications. While Connectionist Temporal Classification (CTC) is a widely used approach for such tasks due to its efficiency, it often…
High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditional audio compression methods and contemporary neural codecs…
The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…
With the exponential growth of video traffic, traditional video streaming systems are approaching their limits in compression efficiency and communication capacity. To further reduce bitrate while maintaining quality, we propose Promptus, a…
Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate…