Related papers: Rethinking Leveraging Pre-Trained Multi-Layer Repr…

Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative embeddings do not always represent speech features such as…

Despite achieving satisfactory performance in speaker verification using deep neural networks, variable-duration utterances remain a challenge that threatens the robustness of systems. To deal with this issue, we propose a speaker…

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…

Distance Metric Learning (DML) has typically dominated the audio-visual speaker verification problem space, owing to strong performance in new and unseen classes. In our work, we explored multitask learning techniques to further enhance…

In speaker verification, the extraction of voice representations is mainly based on the Residual Neural Network (ResNet) architecture. ResNet is built upon convolution layers which learn filters to capture local spatial patterns along all…

Language-queried Audio Separation (LASS) employs linguistic queries to isolate target sounds based on semantic descriptions. However, existing methods face challenges in aligning complex auditory features with linguistic context while…

Speaker diarization is the process of labeling different speakers in a speech signal. Deep speaker embeddings are generally extracted from short speech segments and clustered to determine the segments belong to same speaker identity. The…

This study addresses the problem of single-channel Automatic Speech Recognition of a target speaker within an overlap speech scenario. In the proposed method, the hidden representations in the acoustic model are modulated by speaker…

In this paper we propose a method to model speaker and session variability and able to generate likelihood ratios using neural networks in an end-to-end phrase dependent speaker verification system. As in Joint Factor Analysis, the model…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

This paper is concerned with the task of speaker verification on audio with multiple overlapping speakers. Most speaker verification systems are designed with the assumption of a single speaker being present in a given audio segment.…

Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform…

This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for…

Speech Emotion Recognition (SER) analyzes human emotions expressed through speech. Self-supervised learning (SSL) offers a promising approach to SER by learning meaningful representations from a large amount of unlabeled audio data.…

Spoken Language Assessment (SLA) estimates a learner's oral proficiency from spontaneous speech. The growing population of L2 English speakers has intensified the demand for reliable SLA, a critical component of Computer Assisted Language…

The success of automatic speaker verification shows that discriminative speaker representations can be extracted from neutral speech. However, as a kind of non-verbal voice, laughter should also carry speaker information intuitively. Thus,…

Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a…

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in English, ignoring multilingual spoken content. To address this,…

We propose to address online speaker diarization as a combination of incremental clustering and local diarization applied to a rolling buffer updated every 500ms. Every single step of the proposed pipeline is designed to take full advantage…