Related papers: Task-specific Optimization of Virtual Channel Line…
We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…
Real-time audio-visual speech enhancement (AVSE) is a key enabler for immersive and interactive multimedia services, yet its performance is tightly constrained by network latency, uplink capacity, and computational delay. This paper…
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…
Modern front-end design for speech deepfake detection relies on full fine-tuning of large pre-trained models like XLSR. However, this approach is not parameter-efficient and may lead to suboptimal generalization to realistic, in-the-wild…
Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…
The scarcity of labeled far-field speech is a constraint for training superior far-field speaker verification systems. Fine-tuning the model pre-trained on large-scale near-field speech substantially outperforms training from scratch.…
Personal Voice Activity Detection (PVAD) is crucial for identifying target speaker segments in the mixture, yet its performance heavily depends on the quality of speaker embeddings. A key practical limitation is the short enrollment…
To cope with reverberation and noise in single channel acoustic scenarios, typical supervised deep neural network~(DNN)-based techniques learn a mapping from reverberant and noisy input features to a user-defined target. Commonly used…
We propose a semi-supervised approach to acoustic source localization in reverberant environments based on deep generative modeling. Localization in reverberant environments remains an open challenge. Even with large data volumes, the…
Recent advances in deep learning have facilitated the design of speaker verification systems that directly input raw waveforms. For example, RawNet extracts speaker embeddings from raw waveforms, which simplifies the process pipeline and…
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…
We present ESPnet-SE, which is designed for the quick development of speech enhancement and speech separation systems in a single framework, along with the optional downstream speech recognition module. ESPnet-SE is a new project which…
This paper addresses the problem of automatic speech recognition (ASR) of a target speaker in background speech. The novelty of our approach is that we focus on a wakeup keyword, which is usually used for activating ASR systems like smart…
This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…
Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas…
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions.…
Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate a target speaker's voice from multi-speaker environments by leveraging visual cues as guidance. However, the performance of AV-TSE systems heavily relies on the quality of…
Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder architectures with one-step inference. Inspired by test-time…
Isolating the desired speaker's voice amidst multiplespeakers in a noisy acoustic context is a challenging task. Per-sonalized speech enhancement (PSE) endeavours to achievethis by leveraging prior knowledge of the speaker's voice.Recent…
Speech enhancement, particularly denoising, is vital in improving the intelligibility and quality of speech signals for real-world applications, especially in noisy environments. While prior research has introduced various deep learning…