Related papers: iPhonMatchNet: Zero-Shot User-Defined Keyword Spot…

Deep neural networks (DNNs) have shown promising results for acoustic echo cancellation (AEC). But the DNN-based AEC models let through all near-end speakers including the interfering speech. In light of recent studies on personalized…

Despite remarkable advancements in recent voice conversion (VC) systems, enhancing speaker similarity in zero-shot scenarios remains challenging. This challenge arises from the difficulty of generalizing and adapting speaker characteristics…

Automatic phonemic transcription tools are useful for low-resource language documentation. However, due to the lack of training sets, only a tiny fraction of languages have phonemic transcription tools. Fortunately, multilingual acoustic…

We demonstrate that a production-quality keyword-spotting model can be trained on-device using federated learning and achieve comparable false accept and false reject rates to a centrally-trained model. To overcome the algorithmic…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Few-shot keyword spotting aims to detect previously unseen keywords with very limited labeled samples. A pre-training and adaptation paradigm is typically adopted for this task. While effective in clean conditions, most existing approaches…

The task of audio captioning is similar in essence to tasks such as image and video captioning. However, it has received much less attention. We propose three desiderata for captioning audio -- (i) fluency of the generated text, (ii)…

Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accuracy and low latency for accurate and fast responsiveness.…

Robust and far-field speech recognition is critical to enable true hands-free communication. In far-field conditions, signals are attenuated due to distance. To improve robustness to loudness variation, we introduce a novel frontend called…

In this paper, we present KeyMatchNet, a novel network for zero-shot pose estimation in 3D point clouds. Our method uses only depth information, making it more applicable for many industrial use cases, as color information is seldom…

The emergence of self-supervised representation (i.e., wav2vec 2.0) allows speaker-recognition approaches to process spoken signals through foundation models built on speech data. Nevertheless, effective fusion on the representation…

The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical…

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data.…

By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio. Previous work has shown that a neural AEC model operating on log-mel spectral features (denoted "logmel"…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

We investigate unsupervised models that can map a variable-duration speech segment to a fixed-dimensional representation. In settings where unlabelled speech is the only available resource, such acoustic word embeddings can form the basis…