相关论文: Trainable Frontend For Robust and Far-Field Keywor…

Preference feedback collected by human or VLM annotators is often noisy, presenting a significant challenge for preference-based reinforcement learning that relies on accurate preference labels. To address this challenge, we propose TREND,…

Speech deepfake detection is a well-established research field with different models, datasets, and training strategies. However, the lack of standardized implementations and evaluation protocols limits reproducibility, benchmarking, and…

Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from hands-free communication systems. This is a challenging…

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

In this paper the task of emotion recognition from speech is considered. Proposed approach uses deep recurrent neural network trained on a sequence of acoustic features calculated over small speech intervals. At the same time special…

After their introduction to robust speech recognition, power normalized cepstral coefficient (PNCC) features were successfully adopted to other tasks, including speaker verification. However, as a feature extractor with long-term operations…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental…

In speech deepfake detection, one of the critical aspects is developing detectors able to generalize on unseen data and distinguish fake signals across different datasets. Common approaches to this challenge involve incorporating diverse…

In response to the increasing interest in human--machine communication across various domains, this paper introduces a novel approach called iPhonMatchNet, which addresses the challenge of barge-in scenarios, wherein user speech overlaps…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is that the appropriate noise reduction level differs depending…

Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition. Robustness of distant speech recognition in adverse acoustic…

Keyword Spotting nowadays is an integral part of speech-oriented user interaction targeted for smart devices. To this extent, neural networks are extensively used for their flexibility and high accuracy. However, coming up with a suitable…

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of…

The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components…

Adaptive filters (AFs) are vital for enhancing the performance of downstream tasks, such as speech recognition, sound event detection, and keyword spotting. However, traditional AF design prioritizes isolated signal-level objectives, often…

The expanding feature set of modern headphones puts a challenge on the design of their control interface. Users may want to separately control each feature or quickly switch between modes that activate different features. Traditional…