Related papers: Reducing Bias in Production Speech Models
Human biases have been shown to influence the performance of models and algorithms in various fields, including Natural Language Processing. While the study of this phenomenon is garnering focus in recent years, the available resources are…
Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…
There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate…
Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not…
Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…
It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…
Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…
Recent trends in neural network based text-to-speech/speech synthesis pipelines have employed recurrent Seq2seq architectures that can synthesize realistic sounding speech directly from text characters. These systems however have complex…
With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology…
Decision making algorithms are used in a multitude of different applications. Conventional approaches for designing decision algorithms employ principled and simplified modelling, based on which one can determine decisions via tractable…
Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is…
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.…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…
Speech technologies are deployed in high-stakes settings, yet fairness concerns remain fragmented across tasks and disciplines. Existing surveys either adopt a general machine-learning perspective that overlooks speech-specific properties…
The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…
The performance of deep neural networks is strongly influenced by the quality of their training data. However, mitigating dataset bias by manually curating challenging edge cases remains a major bottleneck. To address this, we propose an…
Accurately measuring discrimination in machine learning-based automated decision systems is required to address the vital issue of fairness between subpopulations and/or individuals. Any bias in measuring discrimination can lead to either…
Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers. However, these systems do not always generalize well for…