Search Results for author:
Found 24 papers, 12 papers with code
EnCodecMAE: Leveraging neural codecs for universal audio representation learning
The goal of universal audio representation learning is to obtain foundational models that can be used for a variety of downstream tasks involving speech, music or environmental sounds.
Mispronunciation detection using self-supervised speech representations
We compare two downstream approaches: 1) training the model for phone recognition (PR) using native English data, and 2) training a model directly for the target task using non-native English data.
Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models
These models are usually trained with a very large amount of unsupervised text data and adapted to perform a downstream natural language task using methods like fine-tuning, calibration or in-context learning.
Deployment of Image Analysis Algorithms under Prevalence Shifts
Domain gaps are among the most relevant roadblocks in the clinical translation of machine learning (ML)-based solutions for medical image analysis.
Phone and speaker spatial organization in self-supervised speech representations
In this work, we analyze the spatial organization of phone and speaker information in several state-of-the-art speech representations using methods that do not require a downstream model.
Understanding metric-related pitfalls in image analysis validation
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice.
Analysis and Comparison of Classification Metrics
Some of the most common ones for measuring quality of hard decisions are standard and balanced accuracy, standard and balanced error rate, F-beta score, and Matthews correlation coefficient (MCC).
Metrics reloaded: Recommendations for image analysis validation
The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output.
Study on the Fairness of Speaker Verification Systems on Underrepresented Accents in English
In this work, we analyze the performance of several state-of-the-art SV systems across groups defined by the accent of the speakers when speaking English.
A Discriminative Hierarchical PLDA-based Model for Spoken Language Recognition
We show that this hierarchical approach consistently outperforms the non-hierarchical one for detection of highly related languages, in many cases by large margins.
Impact of class imbalance on chest x-ray classifiers: towards better evaluation practices for discrimination and calibration performance
This work aims to analyze standard evaluation practices adopted by the research community when assessing chest x-ray classifiers, particularly focusing on the impact of class imbalance in such appraisals.
A transfer learning based approach for pronunciation scoring
Phone-level pronunciation scoring is a challenging task, with performance far from that of human annotators.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Study of positional encoding approaches for Audio Spectrogram Transformers
Transformers have revolutionized the world of deep learning, specially in the field of natural language processing.
Common Limitations of Image Processing Metrics: A Picture Story
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation.
Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings
Emotion recognition datasets are relatively small, making the use of the more sophisticated deep learning approaches challenging.
Out of a hundred trials, how many errors does your speaker verifier make?
For perfect calibration, the Bayes error-rate is upper bounded by min(EER, P, 1-P), where EER is the equal-error-rate and P, 1-P are the prior probabilities of the competing hypotheses.
A Study on the Manifestation of Trust in Speech
An automatic prediction of the level of trust that a user has on a certain system could be used to attempt to correct potential distrust by having the system take relevant actions like, for example, apologizing or explaining its decisions.
A Speaker Verification Backend with Robust Performance across Conditions
When trained on a number of diverse datasets that are labeled only with respect to speaker, the proposed backend consistently and, in some cases, dramatically improves calibration, compared to the standard PLDA approach, on a number of held-out datasets, some of which are markedly different from the training data.
Detecting Distrust Towards the Skills of a Virtual Assistant Using Speech
Research has shown that trust is an essential aspect of human-computer interaction directly determining the degree to which the person is willing to use the system.
A Speaker Verification Backend for Improved Calibration Performance across Varying Conditions
In a recent work, we presented a discriminative backend for speaker verification that achieved good out-of-the-box calibration performance on most tested conditions containing varying levels of mismatch to the training conditions.
A discriminative condition-aware backend for speaker verification
However, unlike the standard backends, all parameters of the model are jointly trained to optimize the binary cross-entropy for the speaker verification task.
Joint PLDA for Simultaneous Modeling of Two Factors
The approach does not change the basic form of PLDA but rather modifies the training procedure to consider the dependency across samples of the latent variable that models within-class variability.
Scoring Formulation for Multi-Condition Joint PLDA
The original work considered a single nuisance condition, deriving the EM and scoring formulas for this scenario.
Joint Probabilistic Linear Discriminant Analysis
In this work, we propose a generalization of this model where the within-speaker variability is not necessarily assumed independent across samples but dependent on another discrete variable.
