相关论文: UFANS: U-shaped Fully-Parallel Acoustic Neural Str…

Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from…

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

This paper proposes a novel approach for speech signal prediction based on a recurrent neural network (RNN). Unlike existing RNN-based predictors, which operate on parametric features and are trained offline on a large collection of such…

Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly…

We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-style datasets. In…

This project develops and trains a Recurrent Neural Network (RNN) that monitors sleeping infants from an auxiliary microphone for cases of Sudden Infant Death Syndrome (SIDS), manifested in sudden or gradual respiratory arrest. To minimize…

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…

Deep learning is at the core of recent spoken language understanding (SLU) related tasks. More precisely, deep neural networks (DNNs) drastically increased the performances of SLU systems, and numerous architectures have been proposed. In…

Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…

For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking…

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and…

Speech recognition systems have improved dramatically over the last few years, however, their performance is significantly degraded for the cases of accented or impaired speech. This work explores domain adversarial neural networks (DANN)…

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

Recently, recurrent neural networks have become state-of-the-art in acoustic modeling for automatic speech recognition. The long short-term memory (LSTM) units are the most popular ones. However, alternative units like gated recurrent unit…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory…

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Silent Speech Interfaces aim to reconstruct the acoustic signal from a sequence of ultrasound tongue images that records the articulatory movement. The extraction of information about the tongue movement requires us to efficiently process…

Neural speech synthesis models have recently demonstrated the ability to synthesize high quality speech for text-to-speech and compression applications. These new models often require powerful GPUs to achieve real-time operation, so being…

The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local…