Search Results for author:
Found 40 papers, 7 papers with code
Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic
On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs).
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
We explore options to use Transformer networks in neural transducer for end-to-end speech recognition.
Towards end-to-end spoken language understanding
Spoken language understanding system is traditionally designed as a pipeline of a number of components.
Natural Language Understanding
Spoken Language Understanding
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
For a low latency scenario with an average latency of 80 ms, Emformer achieves WER $3. 01\%$ on test-clean and $7. 09\%$ on test-other.
Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control
Connected and autonomous vehicles (CAVs) promise next-gen transportation systems with enhanced safety, energy efficiency, and sustainability.
End-to-end contextual speech recognition using class language models and a token passing decoder
In this work, we focus on contextual speech recognition, which is particularly challenging for E2E models because it introduces significant mismatch between training and test data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Transformer-based Acoustic Modeling for Hybrid Speech Recognition
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition.
Ranked #23 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.
Training ASR models by Generation of Contextual Information
Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data.
Improving N-gram Language Models with Pre-trained Deep Transformer
Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference.
Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory
The memory bankstores the embedding information for all the processed seg-ments.
Weak-Attention Suppression For Transformer Based Speech Recognition
Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
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 #17 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications
We compare the transformer based acoustic models with their LSTM counterparts on industrial scale tasks.
Streaming Simultaneous Speech Translation with Augmented Memory Transformer
Transformer-based models have achieved state-of-the-art performance on speech translation tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Large topological Hall effect near room temperature in noncollinear ferromagnet LaMn2Ge2 single crystal
Non-trivial spin structures in itinerant magnets can give rise to topological Hall effect (THE) due to the interacting local magnetic moments and conductive electrons.
Strongly Correlated Electrons
Robust Almost Global Splay State Stabilization of Pulse Coupled Oscillators
This technical note deals with the problem of asymptotically stabilizing the splay state configuration of a network of identical pulse coupled oscillators through the design of the their phase response function.
Global Synchronization of Pulse-Coupled Oscillator Networks Under Byzantine Attacks
Given the distributed and unattended nature of wireless sensor networks, it is imperative to enhance the resilience of PCO synchronization against malicious attacks.
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio.
Ranked #1 on
Speech Recognition
on Common Voice
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Unsupervised Data Selection via Discrete Speech Representation for ASR
Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Decentralized Stochastic Optimization with Inherent Privacy Protection
Decentralized stochastic optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing.
Quantization enabled Privacy Protection in Decentralized Stochastic Optimization
In combination with the presented quantization scheme, the proposed algorithm ensures, for the first time, rigorous differential privacy in decentralized stochastic optimization without losing provable convergence accuracy.
Accelerating RNN-T Training and Inference Using CTC guidance
We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model.
Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy
The new algorithm allows the incorporation of persistent additive noise to enable rigorous differential privacy for data samples, gradients, and intermediate optimization variables without losing provable convergence, and thus circumventing the dilemma of trading accuracy for privacy in differential privacy design.
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
AudioPaLM: A Large Language Model That Can Speak and Listen
AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2.
Locally Differentially Private Distributed Online Learning with Guaranteed Optimality
Distributed online learning is gaining increased traction due to its unique ability to process large-scale datasets and streaming data.
MFMAN-YOLO: A Method for Detecting Pole-like Obstacles in Complex Environment
To solve the problem that the feature information of pole-like obstacles in complex environments is easily lost, resulting in low detection accuracy and low real-time performance, a multi-scale hybrid attention mechanism detection algorithm is proposed in this paper.
Microvasculature Segmentation in Human BioMolecular Atlas Program (HuBMAP)
Image segmentation serves as a critical tool across a range of applications, encompassing autonomous driving's pedestrian detection and pre-operative tumor delineation in the medical sector.
Enhanced Residual SwinV2 Transformer for Learned Image Compression
In particular, our method achieves comparable results while reducing model complexity by 56% compared to these recent methods.
Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation
Then we only encode non-zero channels in the encoding and decoding process, which can greatly reduce the encoding and decoding time.
USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models
We show that the USM-SCD model can achieve more than 75% average speaker change detection F1 score across a test set that consists of data from 96 languages.
SLM: Bridge the thin gap between speech and text foundation models
We present a joint Speech and Language Model (SLM), a multitask, multilingual, and dual-modal model that takes advantage of pretrained foundational speech and language models.
Locally Differentially Private Gradient Tracking for Distributed Online Learning over Directed Graphs
To the best of our knowledge, this is the first result that simultaneously ensures learning accuracy and rigorous local differential privacy in distributed online learning over directed graphs.
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck.
Privacy-Preserving Distributed Optimization and Learning
We first discuss cryptography, differential privacy, and other techniques that can be used for privacy preservation and indicate their pros and cons for privacy protection in distributed optimization and learning.
Privacy in Multi-agent Systems
With the increasing awareness of privacy and the deployment of legislations in various multi-agent system application domains such as power systems and intelligent transportation, the privacy protection problem for multi-agent systems is gaining increased traction in recent years.
Quantization Avoids Saddle Points in Distributed Optimization
More specifically, we propose a stochastic quantization scheme and prove that it can effectively escape saddle points and ensure convergence to a second-order stationary point in distributed nonconvex optimization.
S2LIC: Learned Image Compression with the SwinV2 Block, Adaptive Channel-wise and Global-inter Attention Context
In this paper, we propose an Adaptive Channel-wise and Global-inter attention Context (ACGC) entropy model, which can efficiently achieve dual feature aggregation in both inter-slice and intraslice contexts.
