Related papers: Self-FiLM: Conditioning GANs with self-supervised …

Compared with air-conducted speech, bone-conducted speech has the unique advantage of shielding background noise. Enhancement of bone-conducted speech helps to improve its quality and intelligibility. In this paper, a novel CycleGAN with…

This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising systems towards a particular test-time speaker can improve…

Spoofing countermeasure (CM) and automatic speaker verification (ASV) sub-systems can be used in tandem with a backend classifier as a solution to the spoofing aware speaker verification (SASV) task. The two sub-systems are typically…

Expanding new functionalities efficiently is an ongoing challenge for single-turn task-oriented dialogue systems. In this work, we explore functionality-specific semi-supervised learning via self-training. We consider methods that augment…

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While…

Many speech processing tasks involve measuring the acoustic similarity between speech segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping speech segments of arbitrary duration to fixed-dimensional vectors.…

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

The standard approach to modern self-supervised learning is to generate random views through data augmentations and minimise a loss computed from the representations of these views. This inherently encourages invariance to the…

Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics…

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are…

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work…

We propose a novel method that combines CycleGAN and inter-domain losses for semi-supervised end-to-end automatic speech recognition. Inter-domain loss targets the extraction of an intermediate shared representation of speech and text…

Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input. To remedy this issue, we propose a self-attention layer…

We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech…

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…

The performance of automatic speaker verification (ASV) systems could be degraded by voice spoofing attacks. Most existing works aimed to develop standalone spoofing countermeasure (CM) systems. Relatively little work targeted at developing…

Steady-state visual evoked potentials (SSVEPs) based brain-computer interface (BCI) has received considerable attention due to its high information transfer rate (ITR) and available quantity of targets. However, the performance of frequency…

Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and…

Speech enhancement systems are typically trained using pairs of clean and noisy speech. In audio-visual speech enhancement (AVSE), there is not as much ground-truth clean data available; most audio-visual datasets are collected in…

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…