Related papers: Boosting Unknown-number Speaker Separation with Tr…

This paper presents a novel design of attention model for text-independent speaker verification. The model takes a pair of input utterances and generates an utterance-level embedding to represent speaker-specific characteristics in each…

In this paper, we apply the variational information bottleneck approach to end-to-end neural diarization with encoder-decoder attractors (EEND-EDA). This allows us to investigate what information is essential for the model. EEND-EDA…

We propose a novel approach to enable the use of large, single-speaker ASR models, such as Whisper, for target speaker ASR. The key claim of this method is that it is much easier to model relative differences among speakers by learning to…

We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band…

A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn…

Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fixed (and known) number of speakers, which limits its…

In this paper, we present a novel framework that jointly performs three tasks: speaker diarization, speech separation, and speaker counting. Our proposed framework integrates speaker diarization based on end-to-end neural diarization (EEND)…

This work addresses the problem of speech separation in the Spanish Language using pre-trained deep learning models. As with many speech processing tasks, large databases in other languages different from English are scarce. Therefore this…

This paper proposes a novel Sequence-to-Sequence Neural Diarization (S2SND) framework to perform online and offline speaker diarization. It is developed from the sequence-to-sequence architecture of our previous target-speaker voice…

Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approaches an individual model is needed for each target speaker.…

In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers.…

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Many of the recent advances in speech separation are primarily aimed at synthetic mixtures of short audio utterances with high degrees of overlap. Most of these approaches need an additional stitching step to stitch the separated speech…

The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

In this paper, we proposed Adapitch, a multi-speaker TTS method that makes adaptation of the supervised module with untranscribed data. We design two self supervised modules to train the text encoder and mel decoder separately with…

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…