Related papers: Task-aware Warping Factors in Mask-based Speech En…

Automatic Speaker Verification (ASV) is the process of identifying a person based on the voice presented to a system. Different synthetic approaches allow spoofing to deceive ASV systems (ASVs), whether using techniques to imitate a voice…

Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

This paper addresses the issue of active speaker detection (ASD) in noisy environments and formulates a robust active speaker detection (rASD) problem. Existing ASD approaches leverage both audio and visual modalities, but non-speech sounds…

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

The understanding and interpretation of speech can be affected by various external factors. The use of face masks is one such factors that can create obstruction to speech while communicating. This may lead to degradation of speech…

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…

Spoofing-robust speaker verification (SASV) combines the tasks of speaker and spoof detection to authenticate speakers under adversarial settings. Many SASV systems rely on fusion of speaker and spoof cues at embedding, score or decision…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diarisation and speech recognition using a single model, a…

Automatic speech recognition (ASR) needs to be robust to speaker differences. Voice Conversion (VC) modifies speaker characteristics of input speech. This is an attractive feature for ASR data augmentation. In this paper, we demonstrate…

It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with a single-channel speech enhancement (SE) front-end. This is generally attributed to the processing distortions caused by the nonlinear…

This paper is a study of performance-efficiency trade-offs in pre-trained models for automatic speech recognition (ASR). We focus on wav2vec 2.0, and formalize several architecture designs that influence both the model performance and its…

Audio-visual speech enhancement (AVSE) methods use both audio and visual features for the task of speech enhancement and the use of visual features has been shown to be particularly effective in multi-speaker scenarios. In the majority of…

Recently audio-visual speech recognition (AVSR), which better leverages video modality as additional information to extend automatic speech recognition (ASR), has shown promising results in complex acoustic environments. However, there is…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

The objective of automatic speaker verification (ASV) systems is to determine whether a given test speech utterance corresponds to a claimed enrolled speaker. These systems have a wide range of applications, and ensuring their reliability…

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…

Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achieve consistent efficacy under small volume perturbations and…

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…