Related papers: Masked Proxy Loss For Text-Independent Speaker Ver…

Transformer-based models attain excellent results and generalize well when trained on sufficient amounts of data. However, constrained by the limited data available in the audio domain, most transformer-based models for audio tasks are…

Although few-shot learning has attracted much attention from the fields of image and audio classification, few efforts have been made on few-shot speaker identification. In the task of few-shot learning, overfitting is a tough problem…

In recent years, there has been an increasing focus on user convenience, leading to increased interest in text-based keyword enrollment systems for keyword spotting (KWS). Since the system utilizes text input during the enrollment phase and…

Closed-Set speaker identification aims to assign a speech utterance to one of a predefined set of enrolled speakers and requires robust modeling of speaker-specific characteristics across multiple temporal scales. While recent deep learning…

Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…

The mismatch between close-set training and open-set testing usually leads to significant performance degradation for speaker verification task. For existing loss functions, metric learning-based objectives depend strongly on searching…

Deep Metric Learning (DML) models rely on strong representations and similarity-based measures with specific loss functions. Proxy-based losses have shown great performance compared to pair-based losses in terms of convergence speed.…

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue,…

This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust…

Modeling the rich prosodic variations inherent in human speech is essential for generating natural-sounding speech. While speaker embeddings are commonly used as conditioning inputs in personalized speech generation, they are typically…

Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for text-to-speech (TTS). To overcome the fixed lexical coverage…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo…

Unsupervised representation learning has shown remarkable achievement by reducing the performance gap with supervised feature learning, especially in the image domain. In this study, to extend the technique of unsupervised learning to the…

Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space. We relate DML to feasibility problem of finite chance constraints. We show that minimizer…

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To…

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

Recent adoption of deep learning methods to the field of machine lipreading research gives us two options to pursue to improve system performance. Either, we develop end-to-end systems holistically or, we experiment to further our…

Speech separation has been studied in time domain because of lower latency and higher performance compared to time-frequency domain. The masking-based method has been mostly used in time domain, and the other common method (mapping-based)…