Search Results for author:
Found 35 papers, 16 papers with code
Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions
This work is concerned with devising a robust Parkinson's (PD) disease detector from speech in real-world operating conditions using (i) foundational models, and (ii) speech enhancement (SE) methods.
Speech Analysis of Language Varieties in Italy
We leverage self-supervised learning models to tackle this task and analyze differences and similarities between Italy's regional languages.
Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
We propose a novel language-universal approach to end-to-end automatic spoken keyword recognition (SKR) leveraging upon (i) a self-supervised pre-trained model, and (ii) a set of universal speech attributes (manner and place of articulation).
An Investigation of Incorporating Mamba for Speech Enhancement
This work aims to study a scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task.
Ranked #2 on
Speech Enhancement
on VoiceBank + DEMAND
Benchmarking Representations for Speech, Music, and Acoustic Events
Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities.
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output.
Ranked #4 on
Speech Recognition
on WSJ eval92
(using extra training data)
Audio-Visual Speech Recognition
Automatic Speech Recognition
+3
Bayesian adaptive learning to latent variables via Variational Bayes and Maximum a Posteriori
In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models.
Generative error correction for code-switching speech recognition using large language models
In this work, we propose to leverage large language models (LLMs) and lists of hypotheses generated by an ASR to address the CS problem.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints
The proposed joint multilingual model is evaluated through phoneme recognition.
The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction
This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the ac-curacy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments.
S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction
We address the video prediction task by putting forth a novel model that combines (i) our recently proposed hierarchical residual vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel spatiotemporal PixelCNN (ST-PixelCNN).
How word semantics and phonology affect handwriting of Alzheimer's patients: a machine learning based analysis
Using kinematic properties of handwriting to support the diagnosis of neurodegenerative disease is a real challenge: non-invasive detection techniques combined with machine learning approaches promise big steps forward in this research field.
A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models
We propose a multi-dimensional structured state space (S4) approach to speech enhancement.
Differentially Private Adapters for Parameter Efficient Acoustic Modeling
Evaluated on the open-access Multilingual Spoken Words (MLSW) dataset, our solution reduces the number of trainable parameters by 97. 5% using the RAs with only a 4% performance drop with respect to fine-tuning the cross-lingual speech classifier while preserving DP guarantees.
Inference and Denoise: Causal Inference-based Neural Speech Enhancement
This study addresses the speech enhancement (SE) task within the causal inference paradigm by modeling the noise presence as an intervention.
A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues often encountered in training large-scare acoustic models in low-resource scenarios.
An Ensemble Teacher-Student Learning Approach with Poisson Sub-sampling to Differential Privacy Preserving Speech Recognition
We propose an ensemble learning framework with Poisson sub-sampling to effectively train a collection of teacher models to issue some differential privacy (DP) guarantee for training data.
An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition
We evaluate three end-to-end deep models, including LAS, hybrid CTC/attention, and RNN transducer, on the open-source LibriSpeech and TIMIT corpora.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation
We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data.
A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification
In this paper, we propose two techniques, namely joint modeling and data augmentation, to improve system performances for audio-visual scene classification (AVSC).
A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer
We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models for cross-domain knowledge transfer, to address acoustic mismatches between training and testing conditions.
Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition
In this study, we propose a novel adversarial reprogramming (AR) approach for low-resource spoken command recognition (SCR), and build an AR-SCR system.
Exploring Retraining-Free Speech Recognition for Intra-sentential Code-Switching
To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised.
A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC).
PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications.
Ranked #3 on
Keyword Spotting
on Google Speech Commands
(10-keyword Speech Commands dataset metric)
A Two-Stage Approach to Device-Robust Acoustic Scene Classification
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed.
Ranked #1 on
Acoustic Scene Classification
on TAU Urban Acoustic Scenes 2019
(using extra training data)
Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition
Testing on the Google Speech Commands Dataset, the proposed QCNN encoder attains a competitive accuracy of 95. 12% in a decentralized model, which is better than the previous architectures using centralized RNN models with convolutional features.
Ranked #1 on
Keyword Spotting
on Google Speech Commands
(10-keyword Speech Commands dataset metric)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression
In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression.
Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expected feature vectors is upper bounded by the sum of an approximation error, an estimation error, and an optimization error.
Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification
In this paper, we propose a domain adaptation framework to address the device mismatch issue in acoustic scene classification leveraging upon neural label embedding (NLE) and relational teacher student learning (RTSL).
An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
In contrast to building scene models with whole utterances, the ASM-removed sub-utterances, i. e., acoustic utterances without stop acoustic segments, are then used as inputs to the AlexNet-L back-end for final classification.
Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement
Finally, our experiments of multi-channel speech enhancement on a simulated noisy WSJ0 corpus demonstrate that our proposed hybrid CNN-TT architecture achieves better results than both DNN and CNN models in terms of better-enhanced speech qualities and smaller parameter sizes.
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
On Task 1b development data set, we achieve an accuracy of 96. 7\% with a model size smaller than 500KB.
Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network
Finally, in 8-channel conditions, a PESQ of 3. 12 is achieved using 20 million parameters for TTN, whereas a DNN with 68 million parameters can only attain a PESQ of 3. 06.
Maximum a Posteriori Adaptation of Network Parameters in Deep Models
We present a Bayesian approach to adapting parameters of a well-trained context-dependent, deep-neural-network, hidden Markov model (CD-DNN-HMM) to improve automatic speech recognition performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
