Related papers: Trainable Adaptive Score Normalization for Automat…

This paper describes our submission to Task 1 of the Short-duration Speaker Verification (SdSV) challenge 2020. Task 1 is a text-dependent speaker verification task, where both the speaker and phrase are required to be verified. The…

Audio deepfake detection is crucial to combat the malicious use of AI-synthesized speech. Among many efforts undertaken by the community, the ASVspoof challenge has become one of the benchmarks to evaluate the generalizability and…

Automated Scoring (AS), the natural language processing task of scoring essays and speeches in an educational testing setting, is growing in popularity and being deployed across contexts from government examinations to companies providing…

Spoken Language Understanding (SLU) aims to extract structured semantic representations (e.g., slot-value pairs) from speech recognized texts, which suffers from errors of Automatic Speech Recognition (ASR). To alleviate the problem caused…

In this paper, we propose a novel way of addressing text-dependent automatic speaker verification (TD-ASV) by using a shared-encoder with task-specific decoders. An autoregressive predictive coding (APC) encoder is pre-trained in an…

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Automatic recognition of dysarthric speech remains a highly challenging task to date. Neuro-motor conditions and co-occurring physical disabilities create difficulty in large-scale data collection for ASR system development. Adapting SSL…

Audio-visual speech enhancement (AV-SE) is the task of improving speech quality and intelligibility in a noisy environment using audio and visual information from a talker. Recently, deep learning techniques have been adopted to solve the…

Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-specific training, which incurs high data costs and struggles with temporal fidelity in…

Explaining the decisions made by audio spoofing detection models is crucial for fostering trust in detection outcomes. However, current research on the interpretability of detection models is limited to applying XAI tools to post-trained…

Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data. Performing data augmentation on raw waveforms, such as adding noise or…

Humans are adept at leveraging visual cues from lip movements for recognizing speech in adverse listening conditions. Audio-Visual Speech Recognition (AVSR) models follow similar approach to achieve robust speech recognition in noisy…

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel…

General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper…

Compared to hybrid automatic speech recognition (ASR) systems that use a modular architecture in which each component can be independently adapted to a new domain, recent end-to-end (E2E) ASR system are harder to customize due to their…

Automatic Speech Recognition (ASR) systems suffer significant performance degradation in noisy environments, a challenge that is especially severe for low-resource languages such as Persian. Even state-of-the-art models such as Whisper…

This paper proposes a novel, resource-efficient approach to Visual Speech Recognition (VSR) leveraging speech representations produced by any trained Automatic Speech Recognition (ASR) model. Moving away from the resource-intensive trends…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…