Related papers: Embedding a Differentiable Mel-cepstral Synthesis …

Speech synthesis has recently seen significant improvements in fidelity, driven by the advent of neural vocoders and neural prosody generators. However, these systems lack intuitive user controls over prosody, making them unable to rectify…

Despite advances in deep learning, current state-of-the-art speech emotion recognition (SER) systems still have poor performance due to a lack of speech emotion datasets. This paper proposes augmenting SER systems with synthetic emotional…

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…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Current text to speech (TTS) systems usually leverage a cascaded acoustic model and vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer from two limitations: 1) the acoustic model and vocoder are…

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…

We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…

Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of…

While current deep learning (DL)-based beamforming techniques have been proved effective in speech separation, they are often designed to process narrow-band (NB) frequencies independently which results in higher computational costs and…

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and a enhancement…

Neural source-filter (NSF) models are deep neural networks that produce waveforms given input acoustic features. They use dilated-convolution-based neural filter modules to filter sine-based excitation for waveform generation, which is…

We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks:…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Generating expressive and controllable human speech is one of the core goals of generative artificial intelligence, but its progress has long been constrained by two fundamental challenges: the deep entanglement of speech factors and the…

Emotion embedding space learned from references is a straightforward approach for emotion transfer in encoder-decoder structured emotional text to speech (TTS) systems. However, the transferred emotion in the synthetic speech is not…

Extracting features from the speech is the most critical process in speech signal processing. Mel Frequency Cepstral Coefficients (MFCC) are the most widely used features in the majority of the speaker and speech recognition applications,…

Formant synthesis aims to generate speech with controllable formant structures, enabling precise control of vocal resonance and phonetic features. However, while existing formant synthesis approaches enable precise formant manipulation,…

Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\ that text alone cannot contain. In this work we move towards a speech…

We describe the approach to linguistic variation taken by the Motorola speech synthesizer. A pan-dialectal pronunciation dictionary is described, which serves as the training data for a neural network based letter-to-sound converter.…

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on…