相关论文: Speech Enhancement with Multi-granularity Vector Q…

With the popularity of virtual assistants (e.g., Siri, Alexa), the use of speech recognition is now becoming more and more widespread.However, speech signals contain a lot of sensitive information, such as the speaker's identity, which…

This work adapts two recent architectures of generative models and evaluates their effectiveness for the conversion of whispered speech to normal speech. We incorporate the normal target speech into the training criterion of…

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…

The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To…

Deep generative modeling of natural languages has achieved many successes, such as producing fluent sentences and translating from one language into another. However, the development of generative modeling techniques for paraphrase…

Inspired by recent developments in neural speech coding and diffusion-based language modeling, we tackle speech enhancement by modeling the conditional distribution of clean speech codes given noisy speech codes using absorbing discrete…

Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a…

Representations from pre-trained speech foundation models (SFMs) have shown impressive performance in many downstream tasks. However, the potential benefits of incorporating pre-trained SFM representations into speaker voice similarity…

We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise…

Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner.…

Variational auto-encoder (VAE) is an effective neural network architecture to disentangle a speech utterance into speaker identity and linguistic content latent embeddings, then generate an utterance for a target speaker from that of a…

Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech. Previous works introduce the speaker embedding into speech enhancement models by means of concatenation or affine…

Neural speech codecs have achieved strong performance in low-bitrate compression, but residual vector quantization (RVQ) often suffers from unstable training and ineffective decomposition, limiting reconstruction quality and efficiency. We…

Recent work in the field of speech enhancement (SE) has involved the use of self-supervised speech representations (SSSRs) as feature transformations in loss functions. However, in prior work, very little attention has been paid to the…

VQ-VAE, as a mainstream approach of speech tokenizer, has been troubled by ``index collapse'', where only a small number of codewords are activated in large codebooks. This work proposes product-quantized (PQ) VAE with more codebooks but…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

Neural audio coding has emerged as a vivid research direction by promising good audio quality at very low bitrates unachievable by classical coding techniques. Here, end-to-end trainable autoencoder-like models represent the state of the…