Search Results for author:
Found 48 papers, 16 papers with code
Stabilized training of joint energy-based models and their practical applications
The JEM training relies on "positive examples" (i. e. examples from the training data set) as well as on "negative examples", which are samples from the modeled distribution $p(x)$ generated by means of Stochastic Gradient Langevin Dynamics (SGLD).
Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Speech super-resolution/Bandwidth Extension (BWE) can improve downstream tasks like Automatic Speaker Verification (ASV).
Time-domain speech super-resolution with GAN based modeling for telephony speaker verification
We show that our bandwidth extension leads to phenomena such as a shift of telephone (test) embeddings towards wideband (train) signals, a negative correlation of perceptual quality with downstream performance, and condition-independent score calibration.
Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning.
Non-Contrastive Self-Supervised Learning of Utterance-Level Speech Representations
This paper applies a non-contrastive self-supervised learning method on an unlabeled speech corpus to learn utterance-level embeddings.
AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identification
Building on our previous work that used representation learning to classify and detect adversarial attacks, we propose an improvement to it using AdvEst, a method to estimate adversarial perturbation.
Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser
We propose three defenses--denoiser pre-processor, adversarially fine-tuning ASR model, and adversarially fine-tuning joint model of ASR and denoiser.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Then, we propose a two-stage learning solution where we use a pre-trained domain adaptation system for pre-processing in bandwidth extension training.
Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition
In this paper, we 1) investigate the influence of different factors (i. e., model architecture, phonotactic model, type of speech representation) on phone recognition in an unknown language; 2) provide an analysis of which phones transfer well across languages and which do not in order to understand the limitations of and areas for further improvement for automatic phone inventory creation; and 3) present different methods to build a phone inventory of an unseen language in an unsupervised way.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition
The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language.
Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding
We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework to model the signal structure at a higher level, e. g., phone level.
The JHU submission to VoxSRC-21: Track 3
This technical report describes Johns Hopkins University speaker recognition system submitted to Voxceleb Speaker Recognition Challenge 2021 Track 3: Self-supervised speaker verification (closed).
Beyond Isolated Utterances: Conversational Emotion Recognition
While most of the current approaches focus on inferring emotion from isolated utterances, we argue that this is not sufficient to achieve conversational emotion recognition (CER) which deals with recognizing emotions in conversations.
Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios
Further, we show that by training the model in the written text domain and then transfer learning to conversations, we can achieve reasonable performance with less data.
Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems
Also, representations trained to classify attacks against speaker identification can be used also to classify attacks against speaker verification and speech recognition.
What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition
Dialog acts can be interpreted as the atomic units of a conversation, more fine-grained than utterances, characterized by a specific communicative function.
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform.
Balanced End-to-End Monolingual pre-training for Low-Resourced Indic Languages Code-Switching Speech Recognition
In this paper, we exploit the transfer learning approach to design End-to-End (E2E) CS ASR systems for the two low-resourced language pairs using different monolingual speech data and a small set of noisy CS data.
Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation
We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework that can model the signal structure at a higher level e. g. at the phoneme level.
Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification
We investigate it for adapt microphone speech to the telephone domain.
Adversarial Attacks and Defenses for Speech Recognition Systems
We investigate two threat models: a denial-of-service scenario where fast gradient-sign method (FGSM) or weak projected gradient descent (PGD) attacks are used to degrade the model's word error rate (WER); and a targeted scenario where a more potent imperceptible attack forces the system to recognize a specific phrase.
Study of Pre-processing Defenses against Adversarial Attacks on State-of-the-art Speaker Recognition Systems
Such attacks pose severe security risks, making it vital to deep-dive and understand how much the state-of-the-art SR systems are vulnerable to these attacks.
Focus on the present: a regularization method for the ASR source-target attention layer
This paper introduces a novel method to diagnose the source-target attention in state-of-the-art end-to-end speech recognition models with joint connectionist temporal classification (CTC) and attention training.
CopyPaste: An Augmentation Method for Speech Emotion Recognition
Data augmentation is a widely used strategy for training robust machine learning models.
How Phonotactics Affect Multilingual and Zero-shot ASR Performance
Furthermore, we find that a multilingual LM hurts a multilingual ASR system's performance, and retaining only the target language's phonotactic data in LM training is preferable.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Learning Speaker Embedding from Text-to-Speech
TTS with speaker classification loss improved EER by 0. 28\% and 0. 73\% absolutely from a model using only speaker classification loss in LibriTTS and Voxceleb1 respectively.
Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery
We perform segmentation based on the assumption that the frame feature vectors are more similar within a segment than across the segments.
That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages
Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?
Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
x-vectors meet emotions: A study on dependencies between emotion and speaker recognition
Then, we show the effect of emotion on speaker recognition.
Speaker detection in the wild: Lessons learned from JSALT 2019
This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios.
Audio and Speech Processing Sound
Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition
In this paper, we study two different non-autoregressive transformer structure for automatic speech recognition (ASR): A-CMLM and A-FMLM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Unsupervised Feature Enhancement for speaker verification
The approach yielded significant improvements on both real and simulated sets when data augmentation was not used in speaker verification pipeline or augmentation was used only during x-vector training.
Audio and Speech Processing Sound
Feature Enhancement with Deep Feature Losses for Speaker Verification
On BabyTrain corpus, we observe relative gains of 10. 38% and 12. 40% in minDCF and EER respectively.
Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-GANs
We experiment with two adaptation tasks: microphone to telephone and a novel reverberant to clean adaptation with the end goal of improving speaker recognition performance.
Audio and Speech Processing Sound
Hierarchical Transformers for Long Document Classification
BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm.
rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
In the end, a posteriori SNR weighted energy difference is applied to the extended pitch segments of the denoised speech signal for detecting voice activity.
Speaker Sincerity Detection based on Covariance Feature Vectors and Ensemble Methods
Automatic measuring of speaker sincerity degree is a novel research problem in computational paralinguistics.
ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks
We present JHU's system submission to the ASVspoof 2019 Challenge: Anti-Spoofing with Squeeze-Excitation and Residual neTworks (ASSERT).
Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings
Using transcribed speech from nearby languages gives a further 20-30% relative reduction in character error rate.
Attentive Filtering Networks for Audio Replay Attack Detection
In this work, we propose our replay attacks detection system - Attentive Filtering Network, which is composed of an attention-based filtering mechanism that enhances feature representations in both the frequency and time domains, and a ResNet-based classifier.
Low-Resource Contextual Topic Identification on Speech
In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified.
MCE 2018: The 1st Multi-target Speaker Detection and Identification Challenge Evaluation (MCE) Plan, Dataset and Baseline System
The Multitarget Challenge aims to assess how well current speech technology is able to determine whether or not a recorded utterance was spoken by one of a large number of 'blacklisted' speakers.
Audio and Speech Processing Sound
Punctuation Prediction Model for Conversational Speech
The models are trained on the Fisher corpus which includes punctuation annotation.
Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages
Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
An Empirical Evaluation of Zero Resource Acoustic Unit Discovery
Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations.
Automatic Dialect Detection in Arabic Broadcast Speech
We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of 100%.
A Unified Deep Neural Network for Speaker and Language Recognition
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks.
