相关论文: TIMIT Speaker Profiling: A Comparison of Multi-tas…

Weakly Labelled learning has garnered lot of attention in recent years due to its potential to scale Sound Event Detection (SED) and is formulated as Multiple Instance Learning (MIL) problem. This paper proposes a Multi-Task Learning (MTL)…

In recent years, multi-task learning has turned out to be of great success in various applications. Though single model training has promised great results throughout these years, it ignores valuable information that might help us estimate…

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive…

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and…

Automated speaker recognition uses data processing to identify speakers by their voice. Today, automated speaker recognition is deployed on billions of smart devices and in services such as call centres. Despite their wide-scale deployment…

Speaker clustering is the task of forming speaker-specific groups based on a set of utterances. In this paper, we address this task by using Dominant Sets (DS). DS is a graph-based clustering algorithm with interesting properties that fits…

Peer assessment has been widely applied across diverse academic fields over the last few decades and has demonstrated its effectiveness. However, the advantages of peer assessment can only be achieved with high-quality peer reviews.…

The human voice conveys unique characteristics of an individual, making voice biometrics a key technology for verifying identities in various industries. Despite the impressive progress of speaker recognition systems in terms of accuracy, a…

Training speech separation models in the supervised setting raises a permutation problem: finding the best assignation between the model predictions and the ground truth separated signals. This inherently ambiguous task is customarily…

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…

Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitting. Auxiliary tasks…

Identifying emotion from speech is a non-trivial task pertaining to the ambiguous definition of emotion itself. In this work, we adopt a feature-engineering based approach to tackle the task of speech emotion recognition. Formalizing our…

While deep learning models have demonstrated robust performance in speaker recognition tasks, they primarily rely on low-level audio features learned empirically from spectrograms or raw waveforms. However, prior work has indicated that…

In this paper, we present a Linguistic Informed Multi-Task BERT (LIMIT-BERT) for learning language representations across multiple linguistic tasks by Multi-Task Learning (MTL). LIMIT-BERT includes five key linguistic syntax and semantics…

Usable speech criteria are proposed to extract minimally corrupted speech for speaker identification (SID) in co-channel speech. In co-channel speech, either speaker can randomly appear as the stronger speaker or the weaker one at a time.…

This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…

This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other,…