相关论文: SE/BN Adapter: Parametric Efficient Domain Adaptat…

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning.…

Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration…

Semi-parametric Nearest Neighbor Language Models ($k$NN-LMs) have produced impressive gains over purely parametric LMs, by leveraging large-scale neighborhood retrieval over external memory datastores. However, there has been little…

State-of-the-art speaker verification frameworks have typically focused on developing models with increasingly deeper (more layers) and wider (number of channels) models to improve their verification performance. Instead, this paper…

The SpeakerBeam-FE (SBF) method is proposed for speaker extraction. It attempts to overcome the problem of unknown number of speakers in an audio recording during source separation. The mask approximation loss of SBF is sub-optimal, which…

Large language models pretrained on general-domain corpora often exhibit tokenization inefficiencies when applied to specialized domains. Although continual pretraining for domain adaptation partially alleviate performance degradation, it…

We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and…

Voice recognition and speaker identification are vital for applications in security and personal assistants. This paper presents a lightweight 1D-Convolutional Neural Network (1D-CNN) designed to perform speaker identification on minimal…

Recent advancements in Neural Audio Codec (NAC) models have inspired their use in various speech processing tasks, including speech enhancement (SE). In this work, we propose a novel, efficient SE approach by leveraging the pre-quantization…

In speaker verification, the extraction of voice representations is mainly based on the Residual Neural Network (ResNet) architecture. ResNet is built upon convolution layers which learn filters to capture local spatial patterns along all…

Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-based speaker adaptive training is performed by having a set of…

Recent developments in speech emotion recognition (SER) often leverage deep neural networks (DNNs). Comparing and benchmarking different DNN models can often be tedious due to the use of different datasets and evaluation protocols. To…

One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power…

Self-supervised learning (SSL) on large-scale datasets like AudioSet has become the dominant paradigm for audio representation learning. While the continuous influx of new, unlabeled audio presents an opportunity to enrich these static…

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly…

Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…

Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session…

We propose an approach for training speaker identification models in a weakly supervised manner. We concentrate on the setting where the training data consists of a set of audio recordings and the speaker annotation is provided only at the…

In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…

In this work, we investigate the use of embeddings for speaker-adaptive training of DNNs (DNN-SAT) focusing on a small amount of adaptation data per speaker. DNN-SAT can be viewed as learning a mapping from each embedding to transformation…