Related papers: Y-Vector: Multiscale Waveform Encoder for Speaker …
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…
In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use…
Separating different speaker properties from a multi-speaker environment is challenging. Instead of separating a two-speaker signal in signal space like speech source separation, a speaker embedding de-mixing approach is proposed. The…
Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to…
Typically, singing voice conversion (SVC) depends on an embedding vector, extracted from either a speaker lookup table (LUT) or a speaker recognition network (SRN), to model speaker identity. However, singing contains more expressive…
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…
In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…
Deep speaker embeddings have shown promising results in speaker recognition, as well as in other speaker-related tasks. However, some issues are still under explored, for instance, the information encoded in these representations and their…
In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…
In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be extracted efficiently with linear activation in the embedding layer. To understand…
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…
This paper investigates the application of environmental feature representations for room verification tasks and acoustic meta-data estimation. Audio recordings contain both speaker and non-speaker information. We refer to the…
This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…
In this paper, we propose a speaker verification method by an Attentive Multi-scale Convolutional Recurrent Network (AMCRN). The proposed AMCRN can acquire both local spatial information and global sequential information from the input…
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted…
Automatic speaker recognition algorithms typically characterize speech audio using short-term spectral features that encode the physiological and anatomical aspects of speech production. Such algorithms do not fully capitalize on…
Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…
Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…
In this paper, Whisper, a large-scale pre-trained model for automatic speech recognition, is proposed to apply to speaker verification. A partial multi-scale feature aggregation (PMFA) approach is proposed based on a subset of Whisper…
While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker…