Related papers: Feature Normalisation for Robust Speech Recognitio…

Self-normalizing discriminative models approximate the normalized probability of a class without having to compute the partition function. In the context of language modeling, this property is particularly appealing as it may significantly…

Hearables with integrated microphones may offer communication benefits in noisy working environments, e.g. by transmitting the recorded own voice of the user. Systems aiming at reconstructing the clean and full-bandwidth own voice from…

The ability to learn universal audio representations that can solve diverse speech, music, and environment tasks can spur many applications that require general sound content understanding. In this work, we introduce a holistic audio…

In this paper we address the problem of enhancing speech signals in noisy mixtures using a source separation approach. We explore the use of neural networks as an alternative to a popular speech variance model based on supervised…

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e.,…

In this paper we explore audiovisual emotion recognition under noisy acoustic conditions with a focus on speech features. We attempt to answer the following research questions: (i) How does speech emotion recognition perform on noisy data?…

An effective way to increase the noise robustness of automatic speech recognition is to label noisy speech features as either reliable or unreliable (missing) prior to decoding, and to replace the missing ones by clean speech estimates. We…

Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world…

Data noising is an effective technique for regularizing neural network models. While noising is widely adopted in application domains such as vision and speech, commonly used noising primitives have not been developed for discrete…

Speaker adaptation methods aim to create fair quality synthesis speech voice font for target speakers while only limited resources available. Recently, as deep neural networks based statistical parametric speech synthesis (SPSS) methods…

While neural networks have made significant strides in many AI tasks, they remain vulnerable to a range of noise types, including natural corruptions, adversarial noise, and low-resolution artifacts. Many existing approaches focus on…

It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To…

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech…

Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing…

Paralinguistic properties of speech are essential in analyzing and choosing optimal treatment options for patients with speech disorders. However, automatic modeling of these characteristics is difficult due to the lack of labeled speech…

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…

Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model learned from large-scale data towards a task-specific small-scale data scenarios. However, previous studies focus on…

Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker…