相关论文: Differentiable Time-Varying Linear Prediction in t…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Neural vocoders have recently demonstrated high quality speech synthesis, but typically require a high computational complexity. LPCNet was proposed as a way to reduce the complexity of neural synthesis by using linear prediction (LP) to…

Some glottal analysis approaches based upon linear prediction or complex cepstrum approaches have been proved to be effective to estimate glottal source from real speech utterances. We propose a new approach employing both an all-pole…

Deep learning models are widely applied in the signal processing community, yet their inner working procedure is often treated as a black box. In this paper, we investigate the use of eXplainable Artificial Intelligence (XAI) techniques to…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for…

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

We propose a linear prediction (LP)-based waveform generation method via WaveNet vocoding framework. A WaveNet-based neural vocoder has significantly improved the quality of parametric text-to-speech (TTS) systems. However, it is…

Deep learning has dramatically improved the performance of speech recognition systems through learning hierarchies of features optimized for the task at hand. However, true end-to-end learning, where features are learned directly from…

This paper introduces GlOttal-flow LPC Filter (GOLF), a novel method for singing voice synthesis (SVS) that exploits the physical characteristics of the human voice using differentiable digital signal processing. GOLF employs a glottal…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains…

Understanding the lip movement and inferring the speech from it is notoriously difficult for the common person. The task of accurate lip-reading gets help from various cues of the speaker and its contextual or environmental setting. Every…

Recent advancements in visual speech recognition (VSR) have promoted progress in lip-to-speech synthesis, where pre-trained VSR models enhance the intelligibility of synthesized speech by providing valuable semantic information. The success…

We present differentiable particle filters (DPFs): a differentiable implementation of the particle filter algorithm with learnable motion and measurement models. Since DPFs are end-to-end differentiable, we can efficiently train their…

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or…

In this paper, we propose a differentiable WORLD synthesizer and demonstrate its use in end-to-end audio style transfer tasks such as (singing) voice conversion and the DDSP timbre transfer task. Accordingly, our baseline differentiable…

End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. This principle has recently been applied to several prototype…