相关论文: Listen, Adapt, Better WER: Source-free Single-utte…

A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contributions (LHUC) are used to facilitate both speaker adaptive…

We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR). The model consists of a TitaNet based speaker embedding module, a Conformer…

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…

Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide. End-to-end ASR systems are a natural…

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; only unlabeled test data streams are used for continual model…

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only…

Test-Time adaptation (TTA) aims to enhance model robustness against distribution shifts through rapid model adaptation during inference. While existing TTA methods often rely on entropy-based unsupervised training and achieve promising…

Data augmentation (DA) is ubiquitously used in training of Automatic Speech Recognition (ASR) models. DA offers increased data variability, robustness and generalization against different acoustic distortions. Recently, personalization of…

For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous noise adaptation strategies have been derived. In this paper, we…

Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) by accessing both the source and target data. Considering privacy policies or transmission restrictions of source data…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Test-time adaptation (TTA) methods, which generally rely on the model's predictions (e.g., entropy minimization) to adapt the source pretrained model to the unlabeled target domain, suffer from noisy signals originating from 1) incorrect or…

We present an approach to Audio-Visual Speech Recognition that builds on a pre-trained Whisper model. To infuse visual information into this audio-only model, we extend it with an AV fusion module and LoRa adapters, one of the most…

Post-editing in Automatic Speech Recognition (ASR) entails automatically correcting common and systematic errors produced by the ASR system. The outputs of an ASR system are largely prone to phonetic and spelling errors. In this paper, we…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…