Related papers: An open-source voice type classifier for child-cen…

There are growing implications surrounding generative AI in the speech domain that enable voice cloning and real-time voice conversion from one individual to another. This technology poses a significant ethical threat and could lead to…

Audio-recordings collected with a child-worn device are a fundamental tool in child language research. Long-form recordings collected over whole days promise to capture children's input and production with minimal observer bias, and…

While high-performing language models are typically trained on hundreds of billions of words, human children become fluent language users with a much smaller amount of data. What are the features of the data they receive, and how do these…

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Inner speech recognition has gained enormous interest in recent years due to its applications in rehabilitation, developing assistive technology, and cognitive assessment. However, since language and speech productions are a complex…

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Speech foundation models have demonstrated exceptional capabilities in speech-related tasks. Nevertheless, these models often struggle with non-verbal audio data, such as vocalizations, baby crying, etc., which are critical for various…

A key desiderata for inclusive and accessible speech recognition technology is ensuring its robust performance to children's speech. Notably, this includes the rapidly advancing neural network based end-to-end speech recognition systems.…

This paper investigates the use of automatically collected web audio data for the task of spoken language recognition. We generate semi-random search phrases from language-specific Wikipedia data that are then used to retrieve videos from…

To understand why self-supervised learning (SSL) models have empirically achieved strong performances on several speech-processing downstream tasks, numerous studies have focused on analyzing the encoded information of the SSL layer…

Automatic speech recognition systems are part of people's daily lives, embedded in personal assistants and mobile phones, helping as a facilitator for human-machine interaction while allowing access to information in a practically intuitive…

Self-supervised techniques for learning speech representations have been shown to develop linguistic competence from exposure to speech without the need for human labels. In order to fully realize the potential of these approaches and…

We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental trajectory from birth through school age, covering…

Children's speech recognition is a vital, yet largely overlooked domain when building inclusive speech technologies. The major challenge impeding progress in this domain is the lack of adequate child speech corpora; however, recent advances…

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…

In the U.S., approximately 15-17% of children 2-8 years of age are estimated to have at least one diagnosed mental, behavioral or developmental disorder. However, such disorders often go undiagnosed, and the ability to evaluate and treat…

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…

Recent work has shown that recurrent neural networks can be trained to separate individual speakers in a sound mixture with high fidelity. Here we explore convolutional neural network models as an alternative and show that they achieve…

Interactions involving children span a wide range of important domains from learning to clinical diagnostic and therapeutic contexts. Automated analyses of such interactions are motivated by the need to seek accurate insights and offer…