相关论文: QHARMA-GAN: Quasi-Harmonic Neural Vocoder based on…

We present Spectron, a novel approach to adapting pre-trained large language models (LLMs) to perform spoken question answering (QA) and speech continuation. By endowing the LLM with a pre-trained speech encoder, our model becomes able to…

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

We propose a novel approach for time-scale modification of audio signals. Unlike traditional methods that rely on the framing technique or the short-time Fourier transform to preserve the frequency during temporal stretching, our neural…

In recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously,…

Neural network-based methods have recently demonstrated state-of-the-art results on image synthesis and super-resolution tasks, in particular by using variants of generative adversarial networks (GANs) with supervised feature losses.…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

In real-time speech synthesis, neural vocoders often require low-latency synthesis through causal processing and streaming. However, streaming introduces inefficiencies absent in batch synthesis, such as limited parallelism, inter-frame…

This paper presents a neural vocoder named HiNet which reconstructs speech waveforms from acoustic features by predicting amplitude and phase spectra hierarchically. Different from existing neural vocoders such as WaveNet, SampleRNN and…

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real…

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…

The widespread adoption of voice-enabled authentication and audio biometric systems have significantly increased privacy vulnerabilities associated with sensitive speech data. Compliance with privacy regulations such as GDPR's right to be…

Deep learning architectures have made significant progress in terms of performance in many research areas. The automatic speech recognition (ASR) field has thus benefited from these scientific and technological advances, particularly for…

Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has…

We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre.…

Feature-mapping with deep neural networks is commonly used for single-channel speech enhancement, in which a feature-mapping network directly transforms the noisy features to the corresponding enhanced ones and is trained to minimize the…

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

One challenge of integrating speech input with large language models (LLMs) stems from the discrepancy between the continuous nature of audio data and the discrete token-based paradigm of LLMs. To mitigate this gap, we propose a method for…