Related papers: How phonemes contribute to deep speaker models?

Despite significant advances in ASR, the specific acoustic cues models rely on remain unclear. Prior studies have examined such cues on a limited set of phonemes and outdated models. In this work, we apply a feature attribution technique to…

Unsupervised models of representations based on Contrastive Predictive Coding (CPC)[1] are primarily used in spoken language modelling in that they encode phonetic information. In this study, we ask what other types of information are…

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…

Majority of the recent approaches for text-independent speaker recognition apply attention or similar techniques for aggregation of frame-level feature descriptors generated by a deep neural network (DNN) front-end. In this paper, we…

Many hearables contain an in-ear microphone, which may be used to capture the own voice of its user. However, due to the hearable occluding the ear canal, the in-ear microphone mostly records body-conducted speech, typically suffering from…

What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments…

With the rise of Speech Large Language Models (SpeechLLMs), two dominant approaches have emerged for speech processing: discrete tokens and continuous features. Each approach has demonstrated strong capabilities in audio-related processing…

A deep learning approach has been proposed recently to derive speaker identifies (d-vector) by a deep neural network (DNN). This approach has been applied to text-dependent speaker recognition tasks and shows reasonable performance gains…

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not…

Cochlear implants(CIs) are arguably the most successful neural implant, having restored hearing to over one million people worldwide. While CI research has focused on modeling the cochlear activations in response to low-level acoustic…

Previous studies support the idea of merging auditory-based Gabor features with deep learning architectures to achieve robust automatic speech recognition, however, the cause behind the gain of such combination is still unknown. We believe…

We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks:…

Human interlocutors tend to engage in adaptive behavior known as entrainment to become more similar to each other. Isolating the effect of consistency, i.e., speakers adhering to their individual styles, is a critical part of the analysis…

Analyses of self-supervised speech models have begun to reveal where and how they represent different types of information. However, almost all analyses have focused on English. Here, we examine how wav2vec2 models trained on four different…

This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

What makes some types of languages more probable than others? For instance, we know that almost all spoken languages contain the vowel phoneme /i/; why should that be? The field of linguistic typology seeks to answer these questions and,…

In conventional speech recognition, phoneme-based models outperform grapheme-based models for non-phonetic languages such as English. The performance gap between the two typically reduces as the amount of training data is increased. In this…

This study explores the potential of using acoustic features of segmental speech sounds to detect deepfake audio. These features are highly interpretable because of their close relationship with human articulatory processes and are expected…

The objective of this paper is speaker recognition under noisy and unconstrained conditions. We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media.…