Search Results for author:
Found 43 papers, 13 papers with code
On Randomized Classification Layers and Their Implications in Natural Language Generation
In natural language generation tasks, a neural language model is used for generating a sequence of words forming a sentence.
Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
Large transformer-based models have significant potential for speech transcription and translation.
WhisperNER: Unified Open Named Entity and Speech Recognition
In this paper, we introduce WhisperNER, a novel model that allows joint speech transcription and entity recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing
We present HebDB, a weakly supervised dataset for spoken language processing in the Hebrew language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment
Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network
In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Keyword-Guided Adaptation of Automatic Speech Recognition
Automatic Speech Recognition (ASR) technology has made significant progress in recent years, providing accurate transcription across various domains.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Combining Language Models For Specialized Domains: A Colorful Approach
In this work, we introduce a novel approach that integrates domain-specific or secondary LM into general-purpose LM.
DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
Diffusion models have recently been shown to be relevant for high-quality speech generation.
Open-vocabulary Keyword-spotting with Adaptive Instance Normalization
Open vocabulary keyword spotting is a crucial and challenging task in automatic speech recognition (ASR) that focuses on detecting user-defined keywords within a spoken utterance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Baseline for Detecting Out-of-Distribution Examples in Image Captioning
Image captioning research achieved breakthroughs in recent years by developing neural models that can generate diverse and high-quality descriptions for images drawn from the same distribution as training images.
DDKtor: Automatic Diadochokinetic Speech Analysis
These segmentations predicted by the models are used to obtain measures of speech rate and sound duration.
THOR: Threshold-Based Ranking Loss for Ordinal Regression
In this work, we present a regression-based ordinal regression algorithm for supervised classification of instances into ordinal categories.
Self-supervised Speaker Diarization
Specifically, the study focuses on generating high-quality neural speaker representations without any annotated data, as well as on estimating secondary hyperparameters of the model without annotations.
Correcting Mispronunciations in Speech using Spectrogram Inpainting
Grownup learners of a language tweak their speech to match the tutor reference.
DeepFry: Identifying Vocal Fry Using Deep Neural Networks
The classifier is implemented as a multi-headed fully-connected network trained to detect creaky voice, voicing, and pitch, where the last two are used to refine creak prediction.
Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy
This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy.
CNN-based Spoken Term Detection and Localization without Dynamic Programming
In this paper, we propose a spoken term detection algorithm for simultaneous prediction and localization of in-vocabulary and out-of-vocabulary terms within an audio segment.
Redesigning the classification layer by randomizing the class representation vectors
We propose to draw the class vectors randomly and set them as fixed during training, thus invalidating the visual similarities encoded in these vectors.
Fairness in the Eyes of the Data: Certifying Machine-Learning Models
We present a framework that allows to certify the fairness degree of a model based on an interactive and privacy-preserving test.
Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation
Results suggest that our approach surpasses the baseline models and reaches state-of-the-art performance on both data sets.
Phoneme Boundary Detection using Learnable Segmental Features
Phoneme boundary detection plays an essential first step for a variety of speech processing applications such as speaker diarization, speech science, keyword spotting, etc.
Dr.VOT : Measuring Positive and Negative Voice Onset Time in the Wild
Voice Onset Time (VOT), a key measurement of speech for basic research and applied medical studies, is the time between the onset of a stop burst and the onset of voicing.
SpeechYOLO: Detection and Localization of Speech Objects
In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects.
Hide and Speak: Towards Deep Neural Networks for Speech Steganography
Steganography is the science of hiding a secret message within an ordinary public message, which is referred to as Carrier.
Out-of-Distribution Detection using Multiple Semantic Label Representations
Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks.
Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples
Deep learning models have been successfully applied to malware detection.
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Unfortunately, once the models are sold they can be easily copied and redistributed.
Fooling End-to-end Speaker Verification by Adversarial Examples
We also present two black-box attacks: where the adversarial examples were generated with a system that was trained on YOHO, but the attack is on a system that was trained on NTIMIT; and when the adversarial examples were generated with a system that was trained on Mel-spectrum feature set, but the attack is on a system that was trained on MFCC.
Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines.
Houdini: Fooling Deep Structured Prediction Models
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines.
Automatic Measurement of Pre-aspiration
Pre-aspiration is defined as the period of glottal friction occurring in sequences of vocalic/consonantal sonorants and phonetically voiceless obstruents.
Learning Similarity Functions for Pronunciation Variations
This task generalizes problems such as lexical access (the problem of learning the mapping between words and their possible pronunciations), and defining word neighborhoods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Domain Adaptation For Formant Estimation Using Deep Learning
We then freeze the parameters of the trained network and use several different datasets to train an adaptation layer that makes the obtained network universal in the sense that it works well for a variety of speakers and speech domains with very different characteristics.
Automatic measurement of vowel duration via structured prediction
Manually-annotated data were used to train a model that takes as input an arbitrary length segment of the acoustic signal containing a single vowel that is preceded and followed by consonants and outputs the duration of the vowel.
Sequence Segmentation Using Joint RNN and Structured Prediction Models
We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks.
Context-Based Prediction of App Usage
There are around a hundred installed apps on an average smartphone.
Risk Minimization in Structured Prediction using Orbit Loss
Methods that are aimed at risk minimization, such as the structured ramp loss, the structured probit loss and the direct loss minimization require at least two inference operations per training iteration.
Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions
In this work we develop efficient methods for learning random MAP predictors for structured label problems.
Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss
We consider latent structural versions of probit loss and ramp loss.
Direct Loss Minimization for Structured Prediction
In discriminative machine learning one is interested in training a system to optimize a certain desired measure of performance, or loss.
Support Vector Machines with a Reject Option
We consider the problem of binary classification where the classifier may abstain instead of classifying each observation.
