Related papers: Multi-task self-supervised learning for Robust Spe…

Recognizing code-switched speech is challenging for Automatic Speech Recognition (ASR) for a variety of reasons, including the lack of code-switched training data. Recently, we showed that monolingual ASR systems fine-tuned on code-switched…

It is common in everyday spoken communication that we look at the turning head of a talker to listen to his/her voice. Humans see the talker to listen better, so do machines. However, previous studies on audio-visual speaker extraction have…

Speech emotion recognition (SER), the task of identifying the expression of emotion from spoken content, is challenging due to the difficulty in extracting representations that capture emotional attributes from speech. The scarcity of…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

Recently, an audio-visual speech generative model based on variational autoencoder (VAE) has been proposed, which is combined with a nonnegative matrix factorization (NMF) model for noise variance to perform unsupervised speech enhancement.…

Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very…

End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed…

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…

Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with…

Recurrent Neural Networks (RNN) received a vast amount of attention last decade. Recently, the architectures of Recurrent AutoEncoders (RAE) found many applications in practice. RAE can extract the semantically valuable information, called…

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

Spurred by the demand for interpretable models, research on eXplainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP…

Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…

Audio events are quite often overlapping in nature, and more prone to noise than visual signals. There has been increasing evidence for the superior performance of representations learned using sparse dictionaries for applications like…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

The text generation paradigm for audio tasks has opened new possibilities for unified audio understanding. However, existing models face significant challenges in achieving a comprehensive understanding across diverse audio types, such as…

Robust voice activity detection (VAD) is a challenging task in low signal-to-noise (SNR) environments. Recent studies show that speech enhancement is helpful to VAD, but the performance improvement is limited. To address this issue, here we…