Related papers: End-to-end losses based on speaker basis vectors a…

Speaker diarization is usually referred to as the task that determines ``who spoke when'' in a recording. Until a few years ago, all competitive approaches were modular. Systems based on this framework reached state-of-the-art performance…

End-to-end speech recognition systems have achieved competitive results compared to traditional systems. However, the complex transformations involved between layers given highly variable acoustic signals are hard to analyze. In this paper,…

Many methods of sound event detection (SED) based on machine learning regard a segmented time frame as one data sample to model training. However, the sound durations of sound events vary greatly depending on the sound event class, e.g.,…

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions. However, severe performance degradation is still observed in the…

Zero-shot multi-speaker TTS aims to synthesize speech with the voice of a chosen target speaker without any fine-tuning. Prevailing methods, however, encounter limitations at adapting to new speakers of out-of-domain settings, primarily due…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Conventional methods for speech enhancement rely on handcrafted loss functions (e.g., time or frequency domain losses) or deep feature losses (e.g., using WavLM or wav2vec), which often fail to capture subtle signal properties essential for…

Speaker verification is the process by which a speakers claim of identity is tested against a claimed speaker by his or her voice. Speaker verification is done by the use of some parameters (features) from the speakers voice which can be…

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…

Most studies on speaker verification systems focus on long-duration utterances, which are composed of sufficient phonetic information. However, the performances of these systems are known to degrade when short-duration utterances are…

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome the first…

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

While there has been substantial amount of work in speaker diarization recently, there are few efforts in jointly employing lexical and acoustic information for speaker segmentation. Towards that, we investigate a speaker diarization system…

Attractor-based end-to-end diarization is achieving comparable accuracy to the carefully tuned conventional clustering-based methods on challenging datasets. However, the main drawback is that it cannot deal with the case where the number…

This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding extractors…

We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is…

In this paper, we demonstrate a method for training speaker embedding extractors using weak annotation. More specifically, we are using the full VoxCeleb recordings and the name of the celebrities appearing on each video without knowledge…

Machine recognition of an atypical speech like whispered speech, is a challenging task. We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both…

End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the…

Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to feed the input features at multiple depths in the acoustic…