Search Results for author:
Found 41 papers, 11 papers with code
Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre and style, leading to challenges in achieving controllable generation, especially in zero-shot scenarios.
Region-Based Optimization in Continual Learning for Audio Deepfake Detection
To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection.
Geomagnetic and Inertial Combined Navigation Approach Based on Flexible Correction-Model Predictive Control Algorithm
This paper proposes a geomagnetic and inertial combined navigation approach based on the flexible correction-model predictive control algorithm (Fc-MPC).
Long-distance Geomagnetic Navigation in GNSS-denied Environments with Deep Reinforcement Learning
Geomagnetic navigation has drawn increasing attention with its capacity in navigating through complex environments and its independence from external navigation services like global navigation satellite systems (GNSS).
Efficient Streaming LLM for Speech Recognition
Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities.
An Unsupervised Domain Adaptation Method for Locating Manipulated Region in partially fake Audio
However, they overlook the characteristics in target domain that are absent in source domain.
Efficient Neural Common Neighbor for Temporal Graph Link Prediction
However, such methods focus on learning individual node representations, but overlook the pairwise representation learning nature of link prediction and fail to capture the important pairwise features of links such as common neighbors (CN).
Identifying Functional Brain Networks of Spatiotemporal Wide-Field Calcium Imaging Data via a Long Short-Term Memory Autoencoder
The goal of this study is to elucidate and illustrate, qualitatively and quantitatively, the FBNs identified by use of the LSTM-AER method and compare them to those from traditional SBC and ICA.
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
Connectionist temporal classification (CTC) models are known to have peaky output distributions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Bionic Data-driven Approach for Long-distance Underwater Navigation with Anomaly Resistance
We integrate the developed mechanism with the TA-LSTM, and calibrate the predicted heading angles to gain resistance against geomagnetic anomalies.
Attention-Based CNN-BiLSTM for Sleep State Classification of Spatiotemporal Wide-Field Calcium Imaging Data
Comparison with Existing Method: On a 3-hour WFCI recording, the CNN-BiLSTM achieved a kappa of 0. 67, comparable to a kappa of 0. 65 corresponding to the human EEG/EMG-based scoring.
What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms.
Multimodal Representation Learning by Alternating Unimodal Adaptation
This optimization process is controlled by a gradient modification mechanism to prevent the shared head from losing previously acquired information.
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
TorchAudio is an open-source audio and speech processing library built for PyTorch.
Deep learning-based image super-resolution of a novel end-expandable optical fiber probe for application in esophageal cancer diagnostics
Aim: To improve the efficiency of endoscopic screening, we proposed a novel end-expandable endoscopic optical fiber probe for larger field of visualization and employed a deep learning-based image super-resolution (DL-SR) method to overcome the issue of limited sampling capability.
Exploring Speech Enhancement for Low-resource Speech Synthesis
High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection
The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets.
Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detection
Self-supervised speech models are a rapidly developing research topic in fake audio detection.
Adaptive Fake Audio Detection with Low-Rank Model Squeezing
During the inference stage, these adaptation matrices are combined with the existing model to generate the final prediction output.
Scaling Speech Technology to 1,000+ Languages
Expanding the language coverage of speech technology has the potential to improve access to information for many more people.
ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit
ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community.
TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio
To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed.
Anchored Speech Recognition with Neural Transducers
In this paper, we investigate anchored speech recognition to make neural transducers robust to background speech.
Joint localization and classification of breast tumors on ultrasound images using a novel auxiliary attention-based framework
By use of the attention mechanism, the auxiliary lesion-aware network can optimize multi-scale intermediate feature maps and extract rich semantic information to improve classification and localization performance.
A novel adversarial learning strategy for medical image classification
Deep learning (DL) techniques have been extensively utilized for medical image classification.
ADD 2022: the First Audio Deep Synthesis Detection Challenge
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions
This paper presents initial Speech Recognition results on "Casual Conversations" -- a publicly released 846 hour corpus designed to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of metadata, including age, gender, and skin tone.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution.
Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Impact of deep learning-based image super-resolution on binary signal detection
The presented study highlights the urgent need for the objective assessment of DL-SR methods and suggests avenues for improving their efficacy in medical imaging applications.
Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces
In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state-of-the-art results.
Ranked #20 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks
As our motivation is to allow acoustic models to re-examine their input features in light of partial hypotheses we introduce intermediate model heads and loss function.
Transformer-based Acoustic Modeling for Hybrid Speech Recognition
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition.
Ranked #28 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multilingual Graphemic Hybrid ASR with Massive Data Augmentation
Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations.
Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment
Therefore, a framework of the decision-making training and learning is put forward in this paper.
Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework
Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations.
Parallel training of DNNs with Natural Gradient and Parameter Averaging
However, we have another method, an approximate and efficient implementation of Natural Gradient for Stochastic Gradient Descent (NG-SGD), which seems to allow our periodic-averaging method to work well, as well as substantially improving the convergence of SGD on a single machine.
