Related papers: A processing framework to access large quantities …

It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many…

Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. There has been far less work, however, on the zero-shot…

Voice-controlled house-hold devices, like Amazon Echo or Google Home, face the problem of performing speech recognition of device-directed speech in the presence of interfering background speech, i.e., background noise and interfering…

Automatic speech recognition for low-resource languages remains fundamentally constrained by the scarcity of labeled data and computational resources required by state-of-the-art models. We present a systematic investigation into…

Under noisy conditions, automatic speech recognition (ASR) can greatly benefit from the addition of visual signals coming from a video of the speaker's face. However, when multiple candidate speakers are visible this traditionally requires…

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…

Visual context has been shown to be useful for automatic speech recognition (ASR) systems when the speech signal is noisy or corrupted. Previous work, however, has only demonstrated the utility of visual context in an unrealistic setting,…

While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it…

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…

Rapid growth in speech data demands adaptive models, as traditional static methods fail to keep pace with dynamic and diverse speech information. We introduce continuous speech learning, a new set-up targeting at bridging the adaptation gap…

Speech disfluencies, such as filled pauses or repetitions, are disruptions in the typical flow of speech. Stuttering is a speech disorder characterized by a high rate of disfluencies, but all individuals speak with some disfluencies and the…

Wake word (WW) spotting is challenging in far-field not only because of the interference in signal transmission but also the complexity in acoustic environments. Traditional WW model training requires large amount of in-domain WW-specific…

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar…

This paper describes an open-source Python framework for handling datasets for music processing tasks, built with the aim of improving the reproducibility of research projects in music computing and assessing the generalization abilities of…

This work presents a suite of fine-tuned Whisper models for Swedish, trained on a dataset of unprecedented size and variability for this mid-resourced language. As languages of smaller sizes are often underrepresented in multilingual…

Speech embeddings often retain sensitive attributes such as speaker identity, accent, or demographic information, posing risks in biased model training and privacy leakage. We propose WavShape, an information-theoretic speech representation…

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific…

Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we…

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context,…