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

By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is…

Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…

Given the speech generation framework that represents the speaker attribute with an embedding vector, asynchronous voice anonymization can be achieved by modifying the speaker embedding derived from the original speech. However, the…

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be…

This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings,…

Speaker verification has been studied mostly under the single-talker condition. It is adversely affected in the presence of interference speakers. Inspired by the study on target speaker extraction, e.g., SpEx, we propose a unified speaker…

Many speaker localization methods can be found in the literature. However, speaker localization under strong reverberation still remains a major challenge in the real-world applications. This paper proposes two algorithms for localizing…

Personalized or target speech extraction (TSE) typically needs a clean enrollment -- hard to obtain in real-world crowded environments. We remove the essential need for enrollment by predicting, from the mixture itself, a small set of…

Constructing an embedding space for musical instrument sounds that can meaningfully represent new and unseen instruments is important for downstream music generation tasks such as multi-instrument synthesis and timbre transfer. The…

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…

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…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues,…

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper,…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

Speech separation has been extensively studied to deal with the cocktail party problem in recent years. All related approaches can be divided into two categories: time-frequency domain methods and time domain methods. In addition, some…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

Learning speaker-specific features is vital in many applications like speaker recognition, diarization and speech recognition. This paper provides a novel approach, we term Neural Predictive Coding (NPC), to learn speaker-specific…

The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…

Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a linear layer, using either average or attentive pooling…