Related papers: Reducing Bias in Production Speech Models

In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior…

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data…

Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in…

Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code. In order to asses the reliability of these open-ended generation systems, we…

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a…

Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typically approached separately: a machine learning model is…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Dysarthric speech recognition is a challenging task as dysarthric data is limited and its acoustics deviate significantly from normal speech. Model-based speaker adaptation is a promising method by using the limited dysarthric speech to…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops…

To create a more inclusive workplace, enterprises are actively investing in identifying and eliminating unconscious bias (e.g., gender, race, age, disability, elitism and religion) across their various functions. We propose a deep learning…

Recent advances in deep learning show that end-to-end speech to text translation model is a promising approach to direct the speech translation field. In this work, we provide an overview of different end-to-end architectures, as well as…

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the…

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

Addressing biases in AI models is crucial for ensuring fair and accurate predictions. However, obtaining large, unbiased datasets for training can be challenging. This paper proposes a comprehensive approach using multiple methods to remove…

Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…

In the last few years, due to the broad applicability of deep learning to downstream tasks and end-to-end training capabilities, increasingly more concerns about potential biases to specific, non-representative patterns have been raised.…

WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the…