相关论文: Robust MelGAN: A robust universal neural vocoder f…

Pre-trained models for automatic speech recognition (ASR) and speech enhancement (SE) have exhibited remarkable capabilities under matched noise and channel conditions. However, these models often suffer from severe performance degradation…

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…

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To…

This paper presents BemaGANv2, an advanced GAN-based vocoder designed for high-fidelity and long-term audio generation, with a focus on systematic evaluation of discriminator combination strategies. Long-term audio generation is critical…

Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations,…

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. However, previous works usually encode speech into latent using…

Attention based neural TTS is elegant speech synthesis pipeline and has shown a powerful ability to generate natural speech. However, it is still not robust enough to meet the stability requirements for industrial products. Besides, it…

This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio decoder for neural text-to-speech synthesis. Taking as input a mixed sequence of…

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…

Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models…

Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into…

State-of-the-art non-autoregressive text-to-speech (TTS) models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech. For expressive speech datasets however, we observe characteristic audio distortions. We…

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

We present a lightweight adaptable neural TTS system with high quality output. The system is composed of three separate neural network blocks: prosody prediction, acoustic feature prediction and Linear Prediction Coding Net as a neural…

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

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…

Approximately 1.2% of the world's population has impaired voice production. As a result, automatic dysphonic voice detection has attracted considerable academic and clinical interest. However, existing methods for automated voice assessment…

Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms…

Target sound detection (TSD) aims to detect the target sound from a mixture audio given the reference information. Previous methods use a conditional network to extract a sound-discriminative embedding from the reference audio, and then use…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…