Related papers: Towards Explainable Spoofed Speech Attribution and…

Pre-trained models (PTMs) have shown great promise in the speech and audio domain. Embeddings leveraged from these models serve as inputs for learning algorithms with applications in various downstream tasks. One such crucial task is Speech…

It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods…

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…

Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…

Enhancing explainability in speech self-supervised learning (SSL) is important for developing reliable SSL-based speech processing systems. This study probes how speech SSL models encode speaker-specific information via a large-scale…

In the context of spoofing attacks in speaker recognition systems, we observed that the waveform probability mass function (PMF) of genuine speech differs significantly from the PMF of speech resulting from the attacks. This is true for…

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…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

We look into the task of \emph{generalizing} word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, \emph{without} extra contextual…

Despite the recent success of deep learning for many speech processing tasks, single-microphone, speaker-independent speech separation remains challenging for two main reasons. The first reason is the arbitrary order of the target and…

As a form of biometric authentication technology, the security of speaker verification systems is of utmost importance. However, SV systems are inherently vulnerable to various types of attacks that can compromise their accuracy and…

Self-supervised learning (SSL) speech representation models, trained on large speech corpora, have demonstrated effectiveness in extracting hierarchical speech embeddings through multiple transformer layers. However, the behavior of these…

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

Speaker embeddings (x-vectors) extracted from very short segments of speech have recently been shown to give competitive performance in speaker diarization. We generalize this recipe by extracting from each speech segment, in parallel with…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

Embedding methods have achieved success in face recognition by comparing facial features in a latent semantic space. However, in a fully unconstrained face setting, the facial features learned by the embedding model could be ambiguous or…

This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker…

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

Due to the rapid progress of speech synthesis, deepfake detection has become a major concern in the speech processing community. Because it is a critical task, systems must not only be efficient and robust, but also provide interpretable…