Grapheme-to-phoneme (G2P) conversion is the process of generating pronunciation for words based on their written form. It has a highly essential role for natural language processing, text-to-speech synthesis and automatic speech recognition systems. In this paper, we investigate convolutional neural networks (CNN) for G2P conversion. We propose a novel CNN-based sequence-to-sequence (seq2seq) architecture for G2P conversion. Our approach includes an end-to-end CNN G2P conversion with residual connections and, furthermore, a model that utilizes a convolutional neural network (with and without residual connections) as encoder and Bi-LSTM as a decoder. We compare our approach with state-of-the-art methods, including Encoder-Decoder LSTM and Encoder-Decoder Bi-LSTM. Training and inference times, phoneme and word error rates were evaluated on the public CMUDict dataset for US English, and the best performing convolutional neural network-based architecture was also evaluated on the NetTalk dataset. Our method approaches the accuracy of previous state-of-the-art results in terms of phoneme error rate.

As generative AI (GenAI) technologies proliferate, ensuring trust and transparency in digital ecosystems becomes increasingly critical, particularly within democratic frameworks. This article examines decentralized Web3 mechanisms—blockchain, decentralized autonomous organizations (DAOs), and data cooperatives—as foundational tools for enhancing trust in GenAI. These mechanisms are analyzed within the framework of the EU’s AI Act and the Draghi Report, focusing on their potential to support content authenticity, community-driven verification, and data sovereignty. Based on a systematic policy analysis, this article proposes a multi-layered framework to mitigate the risks of AI-generated misinformation. Specifically, as a result of this analysis, it identifies and evaluates seven detection techniques of trust stemming from the action research conducted in the Horizon Europe Lighthouse project called ENFIELD: (i) federated learning for decentralized AI detection, (ii) blockchain-based provenance tracking, (iii) zero-knowledge proofs for content authentication, (iv) DAOs for crowdsourced verification, (v) AI-powered digital watermarking, (vi) explainable AI (XAI) for content detection, and (vii) privacy-preserving machine learning (PPML). By leveraging these approaches, the framework strengthens AI governance through peer-to-peer (P2P) structures while addressing the socio-political challenges of AI-driven misinformation. Ultimately, this research contributes to the development of resilient democratic systems in an era of increasing technopolitical polarization.

Recent studies in text-to-speech synthesis have shown the benefit of using a continuous pitch estimate; one that interpolates fundamental frequency (F0) even when voicing is not present. However, continuous F0 is still sensitive to additive noise in speech signals and suffers from short-term errors (when it changes rather quickly over time). To alleviate these issues, three adaptive techniques have been developed in this article for achieving a robust and accurate F0: (1) we weight the pitch estimates with state noise covariance using adaptive Kalman-filter framework, (2) we iteratively apply a time axis warping on the input frame signal, (3) we optimize all F0 candidates using an instantaneous-frequency-based approach. Additionally, the second goal of this study is to introduce an extension of a novel continuous-based speech synthesis system (i.e., in which all parameters are continuous). We propose adding a new excitation parameter named Harmonic-to-Noise Ratio (HNR) to the voiced and unvoiced components to indicate the degree of voicing in the excitation and to reduce the influence of buzziness caused by the vocoder. Results based on objective and perceptual tests demonstrate that the voice built with the proposed framework gives state-of-the-art speech synthesis performance while outperforming the previous baseline.

This article focuses on developing a system for high-quality synthesized and converted speech by addressing three fundamental principles. Although the noise-like component in the state-of-the-art parametric vocoders (for example, STRAIGHT) is often not accurate enough, a novel analytical approach for modeling unvoiced excitations using a temporal envelope is proposed. Discrete All Pole, Frequency Domain Linear Prediction, Low Pass Filter, and True envelopes are firstly studied and applied to the noise excitation signal in our continuous vocoder. Second, we build a deep learning model based text–to–speech (TTS) which converts written text into human-like speech with a feed-forward and several sequence-to-sequence models (long short-term memory, gated recurrent unit, and hybrid model). Third, a new voice conversion system is proposed using a continuous fundamental frequency to provide accurate time-aligned voiced segments. The results have been evaluated in terms of objective measures and subjective listening tests. Experimental results showed that the proposed models achieved the highest speaker similarity and better quality compared with the other conventional methods.