相关论文: Phoneme Discretized Saliency Maps for Explainable …

In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden…

We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular fine-resolution gradient methods. It is also quantitatively similar or better in accuracy. Our…

Speech impairments in Parkinson's disease (PD) provide significant early indicators for diagnosis. While models for speech-based PD detection have shown strong performance, their interpretability remains underexplored. This study…

In recent years, there has been growing interest in representing speech with discrete tokens, which serve as pseudo-text for speech language models (speechLMs) and as efficient intermediate representations for downstream tasks. These tokens…

Discrete tokens extracted provide efficient and domain adaptable speech features. Their application to disordered speech that exhibits articulation imprecision and large mismatch against normal voice remains unexplored. To improve their…

Deep neural networks (DNNs) are being increasingly used to make predictions from functional magnetic resonance imaging (fMRI) data. However, they are widely seen as uninterpretable "black boxes", as it can be difficult to discover what…

Recent studies have highlighted the potential of discrete tokens derived from self-supervised learning (SSL) models for various speech-related tasks. These tokens serve not only as substitutes for text in language modeling but also as…

Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were…

Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabulary consists of…

In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised…

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate…

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete,…

Recently, the Large Language Model-based Phoneme-to-Grapheme (LLM-P2G) method has shown excellent performance in speech recognition tasks and has become a feasible direction to replace the traditional WFST decoding method. This framework…

Saliency methods generating visual explanatory maps representing the importance of image pixels for model classification is a popular technique for explaining neural network decisions. Hierarchical dynamic masks (HDM), a novel explanatory…

Saliency methods compute heat maps that highlight portions of an input that were most {\em important} for the label assigned to it by a deep net. Evaluations of saliency methods convert this heat map into a new {\em masked input} by…

Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-grapheme conversion…

Improving the interpretability of geospatial artificial intelligence (GeoAI) models has become critically important to open the "black box" of complex AI models, such as deep learning. This paper compares popular saliency map generation…

Speaker verification systems are vulnerable to spoofing attacks which presents a major problem in their real-life deployment. To date, most of the proposed synthetic speech detectors (SSDs) have weighted the importance of different segments…

Changes in speech and language are among the first signs of Parkinson's disease (PD). Thus, clinicians have tried to identify individuals with PD from their voices for years. Doctors can leverage AI-based speech assessments to spot PD…