Related papers: Window Size Versus Accuracy Experiments in Voice A…
Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conventional methods has been demonstrated, the method can suffer…
This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…
Voice timbre attribute detection (vTAD) is the task of determining the relative intensity of timbre attributes between speech utterances. Voice timbre is a crucial yet inherently complex component of speech perception. While deep neural…
Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or…
Reverberation not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to…
Audio-visual learning has demonstrated promising results in many classical speech tasks (e.g., speech separation, automatic speech recognition, wake-word spotting). We believe that introducing visual modality will also benefit speaker…
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…
This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking…
Traditional supervised voice activity detection (VAD) methods work well in clean and controlled scenarios, with performance severely degrading in real-world applications. One possible bottleneck is that speech in the wild contains…
The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's…
Voice controlled virtual assistants (VAs) are now available in smartphones, cars, and standalone devices in homes. In most cases, the user needs to first "wake-up" the VA by saying a particular word/phrase every time he or she wants the VA…
This paper considers wide-band spectrum sensing and optimization for cognitive radio (CR) networks with noise variance uncertainty. It is assumed that the considered wide-band contains one or more white sub-bands. Under this assumption, we…
Reverberation, especially in large rooms, severely degrades speech recognition performance and speech intelligibility. Since direct measurement of room characteristics is usually not possible, blind estimation of reverberation-related…
Recent works show that speech separation guided diarization (SSGD) is an increasingly promising direction, mainly thanks to the recent progress in speech separation. It performs diarization by first separating the speakers and then applying…
We present an architecture for voice trigger detection for virtual assistants. The main idea in this work is to exploit information in words that immediately follow the trigger phrase. We first demonstrate that by including more audio…
Current Active Speaker Detection (ASD) models achieve great results on AVA-ActiveSpeaker (AVA), using only sound and facial features. Although this approach is applicable in movie setups (AVA), it is not suited for less constrained…
Outbound AI calling systems must distinguish voicemail greetings from live human answers in real time to avoid wasted agent interactions and dropped calls. We present a lightweight approach that extracts 15 temporal features from the speech…
Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise,…
Video anomaly detection (VAD) has rapidly advanced by recent development of Vision-Language Models (VLMs). While these models offer superior zero-shot detection capabilities, their immense computational cost and unstable visual grounding…
With the advancement of modern robotics, autonomous agents are now capable of hosting sophisticated algorithms, which enables them to make intelligent decisions. But developing and testing such algorithms directly in real-world systems is…