Related papers: Memory-Efficient Training for Deep Speaker Embeddi…

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…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train…

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome the first…

We propose a novel neural speaker diarization system using memory-aware multi-speaker embedding with sequence-to-sequence architecture (NSD-MS2S), which integrates the strengths of memory-aware multi-speaker embedding (MA-MSE) and…

Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…

Reverberation results in reduced intelligibility for both normal and hearing-impaired listeners. This paper presents a novel psychoacoustic approach of dereverberation of a single speech source by recycling a pre-trained binaural anechoic…

Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale datasets are capable of capturing a diverse set of features, and…

The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of…

Recently, more and more zero-shot voice conversion algorithms have been proposed. As a fundamental part of zero-shot voice conversion, speaker embeddings are the key to improving the converted speech's speaker similarity. In this paper, we…

Deep learning models (DLMs) are state-of-the-art techniques in speech recognition. However, training good DLMs can be time consuming especially for production-size models and corpora. Although several parallel training algorithms have been…

We present a theoretical analysis of GPU memory consumption during the training of DeepSeek models such as DeepSeek-v2 and DeepSeek-v3. Our primary objective is to clarify the device-level memory requirements associated with various…

Verifying the identity of a speaker is crucial in modern human-machine interfaces, e.g., to ensure privacy protection or to enable biometric authentication. Classical speaker verification (SV) approaches estimate a fixed-dimensional…

Deep clustering (DC) and utterance-level permutation invariant training (uPIT) have been demonstrated promising for speaker-independent speech separation. DC is usually formulated as two-step processes: embedding learning and embedding…

Speaker embedding is an important front-end module to explore discriminative speaker features for many speech applications where speaker information is needed. Current SOTA backbone networks for speaker embedding are designed to aggregate…