Related papers: Enrollment-less training for personalized voice ac…

In this paper we present a new method for text-independent speaker verification that combines segmental dynamic time warping (SDTW) and the d-vector approach. The d-vectors, generated from a feed forward deep neural network trained to…

This paper presents a computationally efficient and distributed speaker diarization framework for networked IoT-style audio devices. The work proposes a Federated Learning model which can identify the participants in a conversation without…

This paper addresses the issue of active speaker detection (ASD) in noisy environments and formulates a robust active speaker detection (rASD) problem. Existing ASD approaches leverage both audio and visual modalities, but non-speech sounds…

Speech activity detection (SAD), which often rests on the fact that the noise is "more" stationary than speech, is particularly challenging in non-stationary environments, because the time variance of the acoustic scene makes it difficult…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

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…

Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant…

In this paper, we explore the use of a factorized hierarchical variational autoencoder (FHVAE) model to learn an unsupervised latent representation for dialect identification (DID). An FHVAE can learn a latent space that separates the more…

Dysarthric speech recognition is a challenging task due to acoustic variability and limited amount of available data. Diverse conditions of dysarthric speakers account for the acoustic variability, which make the variability difficult to be…

To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough…

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…

While speech-based depression detection methods that use speaker-identity features, such as speaker embeddings, are popular, they often compromise patient privacy. To address this issue, we propose a speaker disentanglement method that…

Reverberation not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to…

Mispronunciation Detection and Diagnosis (MDD) is crucial for language learning and speech therapy. Unlike conventional methods that require scoring models or training phoneme-level models, we propose a novel training-free framework that…

The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal…

Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful…

Visual speech recognition (VSR) aims to recognize the content of speech based on lip movements, without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development…

In this paper, we propose a solution to allow speaker conditioned speech models, such as VoiceFilter-Lite, to support an arbitrary number of enrolled users in a single pass. This is achieved by using an attention mechanism on multiple…

Audio-visual speaker diarization aims at detecting "who spoke when" using both auditory and visual signals. Existing audio-visual diarization datasets are mainly focused on indoor environments like meeting rooms or news studios, which are…