Related papers: Improving Fairness and Robustness in End-to-End Sp…

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy…

In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…

Automatic Speech Recognition (ASR) systems in real-world settings need to handle imperfect audio, often degraded by hardware limitations or environmental noise, while accommodating diverse user groups. In human-robot interaction (HRI),…

The evaluation of voice anonymisation remains challenging. Current practice relies on automatic speaker verification metrics such as the equal error rate (EER). Performance estimates dependent on the classifier and operating point provide…

Measuring performance of an automatic speech recognition (ASR) system without ground-truth could be beneficial in many scenarios, especially with data from unseen domains, where performance can be highly inconsistent. In conventional ASR…

Joint punctuated and normalized automatic speech recognition (ASR) aims at outputing transcripts with and without punctuation and casing. This task remains challenging due to the lack of paired speech and punctuated text data in most ASR…

Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar…

Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather than characterizing…

For multi-channel speech recognition, speech enhancement techniques such as denoising or dereverberation are conventionally applied as a front-end processor. Deep learning-based front-ends using such techniques require aligned clean and…

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling,…

We present an approach to reduce the performance disparity between geographic regions without degrading performance on the overall user population for ASR. A popular approach is to fine-tune the model with data from regions where the ASR…

Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

Recent studies have explored the use of pre-trained embeddings for speech emotion recognition (SER), achieving comparable performance to conventional methods that rely on low-level knowledge-inspired acoustic features. These embeddings are…

All-neural, end-to-end ASR systems gained rapid interest from the speech recognition community. Such systems convert speech input to text units using a single trainable neural network model. E2E models require large amounts of paired speech…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…

While subgroup disparities and performance bias are increasingly studied in computational research, fairness in categorical Speech Emotion Recognition (SER) remains underexplored. Existing methods often rely on explicit demographic labels,…