相关论文: Pre-Trained Foundation Model representations to un…

The estimation of room impulse responses (RIRs) between static loudspeaker and microphone locations can be done using a number of well-established measurement and inference procedures. While these procedures assume a time-invariant acoustic…

This paper presents a recurrent neural network approach to simulating mechanical ventilator pressure. The traditional mechanical ventilator has a control pressure that is monitored by a medical practitioner and can behave incorrectly if the…

This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT) based multi-speakers ASR system with large-scale simulation…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

In this paper, we introduce a pretrained audio-visual Transformer trained on more than 500k utterances from nearly 4000 celebrities from the VoxCeleb2 dataset for human behavior understanding. The model aims to capture and extract useful…

Pressure-sensitive mats (PSM) have proved to be useful in the estimation of respiratory rates (RR) in adult patients. However, PSM technology has not been extensively applied to derive physiologic parameters in infant and neonatal patients.…

Wav2vec2.0 is a popular self-supervised pre-training framework for learning speech representations in the context of automatic speech recognition (ASR). It was shown that wav2vec2.0 has a good robustness against the domain shift, while the…

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…

We consider the generative modeling of speech over multiple minutes, a requirement for long-form multimedia generation and audio-native voice assistants. However, textless spoken language models struggle to generate plausible speech past…

Respiratory auscultation can help healthcare professionals detect abnormal respiratory conditions if adventitious lung sounds are heard. The state-of-the-art artificial intelligence technologies based on deep learning show great potential…

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason…

This paper presents a reverberation module for source-filter-based neural vocoders that improves the performance of reverberant effect modeling. This module uses the output waveform of neural vocoders as an input and produces a reverberant…

Clinical characterization and interpretation of respiratory sound symptoms have remained a challenge due to the similarities in the audio properties that manifest during auscultation in medical diagnosis. The misinterpretation and…

This paper proposes a new approach to duration modelling for statistical parametric speech synthesis in which a recurrent statistical model is trained to output a phone transition probability at each timestep (acoustic frame). Unlike…

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…

The primary objective of this paper is to build classification models and strategies to identify breathing sound anomalies (wheeze, crackle) for automated diagnosis of respiratory and pulmonary diseases. In this work we propose a deep…

Word error rate (WER) is a metric used to evaluate the quality of transcriptions produced by Automatic Speech Recognition (ASR) systems. In many applications, it is of interest to estimate WER given a pair of a speech utterance and a…

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in…

Speech-based analysis offers a scalable and non-invasive approach for detecting cognitive decline, yet progress has been constrained by the limited availability of clinically validated datasets collected under realistic conditions. We…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…