相关论文: Low-latency Speech Enhancement via Speech Token Ge…

This study compares the performances of different algorithms for coding speech at low bit rates. In addition to widely deployed traditional vocoders, a selection of recently developed generative-model-based coders at different bit rates are…

Recently, generative speech enhancement has garnered considerable interest; however, existing approaches are hindered by excessive complexity, limited efficiency, and suboptimal speech quality. To overcome these challenges, this paper…

This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement, addressing the challenges posed by unpredictable noise conditions and domain shifts. This method combines a main speech enhancement task with a…

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial…

This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.…

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…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Low latency models are critical for real-time speech enhancement applications, such as hearing aids and hearables. However, the sub-millisecond latency space for resource-constrained hearables remains underexplored. We demonstrate speech…

Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond…

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more…

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…

Audio-visual speech enhancement aims to extract clean speech from a noisy environment by leveraging not only the audio itself but also the target speaker's lip movements. This approach has been shown to yield improvements over audio-only…

Single-channel speech enhancement is utilized in various tasks to mitigate the effect of interfering signals. Conventionally, to ensure the speech enhancement performs optimally, the speech enhancement has needed to be tuned for each task.…

Textless spoken language models (SLMs) are generative models of speech that do not rely on text supervision. Most textless SLMs learn to predict the next semantic token, a discrete representation of linguistic content, and rely on a…

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…

Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…

Many neural text-to-speech architectures can synthesize nearly natural speech from text inputs. These architectures must be trained with tens of hours of annotated and high-quality speech data. Compiling such large databases for every new…