Related papers: DAME: Duration-Aware Matryoshka Embedding for Dura…
Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…
In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…
While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…
Speaker embeddings are widely used in speaker verification systems and other applications where it is useful to characterise the voice of a speaker with a fixed-length vector. These embeddings tend to be treated as "black box" encodings,…
In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…
Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative embeddings do not always represent speech features such as…
This paper explores how the in- and out-domain probabilistic linear discriminant analysis (PLDA) speaker verification behave when enrolment and verification lengths are reduced. Experiment studies have found that when full-length utterance…
Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…
A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning and structured network pruning. While there is a growing body…
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of learned concepts)…
Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…
Speech enhancement remains challenging due to the trade-off between efficiency and perceptual quality. In this paper, we introduce MAGE, a Masked Audio Generative Enhancer that advances generative speech enhancement through a compact and…
In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…
High-dimensional embeddings from large language models impose significant storage and computational costs on vector search systems. Recent embedding compression methods, including Matryoshka-Adaptor (EMNLP 2024), Search-Adaptor (ACL 2024),…
We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…
It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To…
Neural speaker embeddings trained using classification objectives have demonstrated state-of-the-art performance in multiple applications. Typically, such embeddings are trained on an out-of-domain corpus on a single task e.g., speaker…
This paper describes the NPU system submitted to Interspeech 2020 Far-Field Speaker Verification Challenge (FFSVC). We particularly focus on far-field text-dependent SV from single (task1) and multiple microphone arrays (task3). The major…
Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…
Generalized end-to-end (GE2E) model is widely used in speaker verification (SV) fields due to its expandability and generality regardless of specific languages. However, the long-short term memory (LSTM) based on GE2E has two limitations:…