相关论文: IEEE SLT 2021 Alpha-mini Speech Challenge: Open Da…

Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper…

This paper introduces SpoofCeleb, a dataset designed for Speech Deepfake Detection (SDD) and Spoofing-robust Automatic Speaker Verification (SASV), utilizing source data from real-world conditions and spoofing attacks generated by…

Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speech representation learning. However, their effectiveness on…

Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical…

This paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study.…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic…

Noise robustness is a key aspect of successful speech applications. Speech enhancement (SE) has been investigated to improve automatic speech recognition accuracy; however, its effectiveness for keyword spotting (KWS) is still…

Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…

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…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

This paper describes the BUT submission to the ESDD 2026 Challenge, specifically focusing on Track 1: Environmental Sound Deepfake Detection with Unseen Generators. To address the critical challenge of generalizing to audio generated by…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

The aim of this project is to implement and design arobust synthetic speech classifier for the IEEE Signal ProcessingCup 2022 challenge. Here, we learn a synthetic speech attributionmodel using the speech generated from various…

Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ…

This paper describes our submitted systems to the ASVspoof 5 Challenge Track 1: Speech Deepfake Detection - Open Condition, which consists of a stand-alone speech deepfake (bonafide vs spoof) detection task. Recently, large-scale…

Deep neural networks provide effective solutions to small-footprint keyword spotting (KWS). However, if training data is limited, it remains challenging to achieve robust and highly accurate KWS in real-world scenarios where unseen sounds…

Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual…

We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind. We discuss SSL for AMs in a small…

Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high…