Related papers: Supervised Speaker Embedding De-Mixing in Two-Spea…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

In reverberant conditions with multiple concurrent speakers, each microphone acquires a mixture signal of multiple speakers at a different location. In over-determined conditions where the microphones out-number speakers, we can narrow down…

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…

Recently, speaker embeddings extracted with deep neural networks became the state-of-the-art method for speaker verification. In this paper we aim to facilitate its implementation on a more generic toolkit than Kaldi, which we anticipate to…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

This work presents a novel back-end framework for speaker verification using graph attention networks. Segment-wise speaker embeddings extracted from multiple crops within an utterance are interpreted as node representations of a graph. The…

This paper describes a spatial-aware speaker diarization system for the multi-channel multi-party meeting. The diarization system obtains direction information of speaker by microphone array. Speaker spatial embedding is generated by…

This paper proposes a novel acoustic word embedding called Acoustic Neighbor Embeddings where speech or text of arbitrary length are mapped to a vector space of fixed, reduced dimensions by adapting stochastic neighbor embedding (SNE) to…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of…

In this study, we propose a modulation decoupling based single channel speech enhancement subspace framework, in which the spectrogram of noisy speech is decoupled as the product of a spectral envelop subspace and a spectral details…

The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications. Several studies solved the SCD task using audio inputs only and have shown limited performance.…

Speaker embedding extractors (EEs), which map input audio to a speaker discriminant latent space, are of paramount importance in speaker diarisation. However, there are several challenges when adopting EEs for diarisation, from which we…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid…

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge.…

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would…

This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well as target speakers' spoofed inputs should be addressed.…

We propose an algorithm that is capable of synthesizing high quality target speaker's singing voice given only their normal speech samples. The proposed algorithm first integrate speech and singing synthesis into a unified framework, and…