Mohammed Salah Al-Radhi

39 papers A 4B 1Journal 17Unranked 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum. CoRR Mohammed Salah Al-Radhi, Riad Larbi, Mátyás Bartalis, Géza Németh
2025	J	`jnl`	Breaking the Silence: Brain-to-Speech Innovations. ERCIM News Mohammed Salah Al-Radhi, Géza Németh
2025	A	`conf`	MiSTR: Multi-Modal iEEG-to-Speech Synthesis with Transformer-Based Prosody Prediction and Neural Phase Reconstruction. INTERSPEECH Mohammed Salah Al-Radhi, Géza Németh, Branislav Gerazov
2025	J	`jnl`	MiSTR: Multi-Modal iEEG-to-Speech Synthesis with Transformer-Based Prosody Prediction and Neural Phase Reconstruction. CoRR Mohammed Salah Al-Radhi, Géza Németh, Branislav Gerazov
2025	—	`conf`	Prompting the Mind: EEG-to-Text Translation with Multimodal LLMs and Semantic Control. SPECOM (1) Mohammed Salah Al-Radhi, Sadi Mahmud Shurid, Géza Németh
2025	J	`jnl`	Retraining-Free Pruning Text-to-Speech Synthesis Model for Speaker Cloning. IEEE Access Ali Raheem Mandeel, Tamara Z. Fadhil, Mohammed Hamzah Alsalihi, Mohammed Salah Al-Radhi, Géza Németh
2025	—	`conf`	Style-Controlled VALL-E for Few-Shot Emotional German TTS. SpeD Rami Kammoun, Mohammed Salah Al-Radhi
2025	J	`jnl`	Trustworthy AI for Whom? GenAI Detection Techniques of Trust Through Decentralized Web3 Ecosystems. Big Data Cogn. Comput. Igor Calzada, Géza Németh, Mohammed Salah Al-Radhi
2024	—	`conf`	ChildTinyTalks (CTT): A Benchmark Dataset and Baseline for Expressive Child Speech Synthesis. SPECOM (1) Shaimaa Alwaisi, Mohammed Salah Al-Radhi, Géza Németh
2023	—	`conf`	Advancing Limited Data Text-to-Speech Synthesis: Non-Autoregressive Transformer for High-Quality Parallel Synthesis. SpeD Mohammed Salah Al-Radhi, Omnia Ibrahim, Ali Raheem Mandeel, Tamás Gábor Csapó, Géza Németh
2023	—	`conf`	Automated Child Voice Generation: Methodology and Implementation. SpeD Shaimaa Alwaisi, Mohammed Salah Al-Radhi, Géza Németh
2023	—	`conf`	Concept and Pictogram-Based User-Interface Design of a Helper Tool for People with Aphasia. dHealth Peter Mayer, Katharina Werner, Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Bálint Czeba, Géza Németh, Ana Patrícia Rocha, Ilídio Castro Oliveira, Samuel S. Silva, Melinda Szeker, António J. S. Teixeira, Paul Panek
2023	—	`conf`	Enhancing End-to-End Speech Synthesis by Modeling Interrogative Sentences with Speaker Adaptation. SpeD Ali Raheem Mandeel, Mohammed Salah Al-Radhi, Tamás Gábor Csapó
2023	J	`jnl`	Investigations on speaker adaptation using a continuous vocoder within recurrent neural network based text-to-speech synthesis. Multim. Tools Appl. Ali Raheem Mandeel, Mohammed Salah Al-Radhi, Tamás Gábor Csapó
2023	—	`conf`	Modeling Irregular Voice in End-to-End Speech Synthesis via Speaker Adaptation. SpeD Ali Raheem Mandeel, Mohammed Salah Al-Radhi, Tamás Gábor Csapó
2023	—	`conf`	Nonparallel Expressive TTS for Unseen Target Speaker using Style-Controlled Adaptive Layer and Optimized Pitch Embedding. SpeD Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2023	—	`conf`	Universal Approach to Multilingual Multispeaker Child Speech SynthesisUniversal Approach to Multilingual Multispeaker Child Speech Synthesis. SSW Shaimaa Alwaisi, Mohammed Salah Al-Radhi, Géza Németh
2022	—	`conf`	Towards Parametric Speech Synthesis Using Gaussian-Markov Model of Spectral Envelope and Wavelet-Based Decomposition of F0. EUSIPCO Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Csaba Zainkó, Géza Németh
2022	J	`jnl`	Towards Parametric Speech Synthesis Using Gaussian-Markov Model of Spectral Envelope and Wavelet-Based Decomposition of F0. CoRR Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Csaba Zainkó, Géza Németh
2021	J	`jnl`	Advances in Speech Vocoding for Text-to-Speech with Continuous Parameters. CoRR Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2021	A	`conf`	Continuous Wavelet Vocoder-Based Decomposition of Parametric Speech Waveform Synthesis. Interspeech Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Csaba Zainkó, Géza Németh
2021	J	`jnl`	Continuous Wavelet Vocoder-based Decomposition of Parametric Speech Waveform Synthesis. CoRR Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Csaba Zainkó, Géza Németh
2021	—	`conf`	Effects of F0 Estimation Algorithms on Ultrasound-Based Silent Speech Interfaces. SpeD Pengyu Dai, Mohammed Salah Al-Radhi, Tamás Gábor Csapó
2021	J	`jnl`	High-Quality Vocoding Design with Signal Processing for Speech Synthesis and Voice Conversion. CoRR Mohammed Salah Al-Radhi
2021	J	`jnl`	Noise and acoustic modeling with waveform generator in text-to-speech and neutral speech conversion. Multim. Tools Appl. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2021	—	`conf`	Speaker Adaptation with Continuous Vocoder-Based DNN-TTS. SPECOM Ali Raheem Mandeel, Mohammed Salah Al-Radhi, Tamás Gábor Csapó
2021	J	`jnl`	Speaker Adaptation with Continuous Vocoder-based DNN-TTS. CoRR Ali Raheem Mandeel, Mohammed Salah Al-Radhi, Tamás Gábor Csapó
2020	J	`jnl`	A continuous vocoder for statistical parametric speech synthesis and its evaluation using an audio-visual phonetically annotated Arabic corpus. Comput. Speech Lang. Mohammed Salah Al-Radhi, Omnia Abdo, Tamás Gábor Csapó, Sherif M. Abdou, Géza Németh, Mervat Fashal
2020	J	`jnl`	Continuous Noise Masking Based Vocoder for Statistical Parametric Speech Synthesis. IEICE Trans. Inf. Syst. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2020	—	`—`	High-Quality Vocoding Design with Signal Processing for Speech Synthesis and Voice Conversion Mohammed Salah Al-Radhi
2019	J	`jnl`	Continuous vocoder applied in deep neural network based voice conversion. Multim. Tools Appl. Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2019	—	`conf`	Parallel Voice Conversion Based on a Continuous Sinusoidal Model. SpeD Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2019	B	`conf`	RNN-based speech synthesis using a continuous sinusoidal model. IJCNN Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2019	J	`jnl`	RNN-based speech synthesis using a continuous sinusoidal model. CoRR Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2019	A	`conf`	Ultrasound-Based Silent Speech Interface Built on a Continuous Vocoder. INTERSPEECH Tamás Gábor Csapó, Mohammed Salah Al-Radhi, Géza Németh, Gábor Gosztolya, Tamás Grósz, László Tóth, Alexandra Markó
2019	J	`jnl`	Ultrasound-based Silent Speech Interface Built on a Continuous Vocoder. CoRR Tamás Gábor Csapó, Mohammed Salah Al-Radhi, Géza Németh, Gábor Gosztolya, Tamás Grósz, László Tóth, Alexandra Markó
2018	—	`conf`	A Continuous Vocoder Using Sinusoidal Model for Statistical Parametric Speech Synthesis. SPECOM Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2017	—	`conf`	Deep Recurrent Neural Networks in Speech Synthesis Using a Continuous Vocoder. SPECOM Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh
2017	A	`conf`	Time-Domain Envelope Modulating the Noise Component of Excitation in a Continuous Residual-Based Vocoder for Statistical Parametric Speech Synthesis. INTERSPEECH Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh