On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,878 papers · 148 categories

Trend · papers per month

count % of corpus

15 results for “BLSTM”

Brazilian Lyrics-Based Music Genre Classification Using a BLSTM Networkcs.CL

Paper classifies Brazilian music genres using song lyrics with BLSTM network.

problem Classifying Brazilian music genres from lyrics.

method Used BLSTM network combined with SVM, Random Forest, and word embeddings.

result BLSTM outperforms other models with an F1-score of 0.48.

Brazilian music genre classification song lyrics BLSTM network word embeddings

2020-03-06abs ↗pdf ↗

Deep Recurrent Neural Networks for Acoustic Modellingcs.LG

We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR). We term our contribution as a TC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (DNN) with Time Convolution (TC), followed by a Bidirectional Long Short-Term Memory (BLSTM), and a fi…

2015-04-07abs ↗pdf ↗

Cumulative Adaptation for BLSTM Acoustic Modelscs.CL

Improved speech recognition with cumulative adaptation methods.

problem Robust speech recognition in varying environments and speakers.

method Used a bidirectional LSTM neural network and i-vectors for adaptation.

result Achieved 13% relative improvement in word error rate.

speech recognition cumulative adaptation BLSTM i-vectors word error rate

2019-06-14abs ↗pdf ↗

Attention-Wrapped Hierarchical BLSTMs for DDI Extractioncs.IR

New model improves DDI extraction with 78.5% macro F1-score.

problem Extracting Drug-Drug Interactions from text.

method Attention-Wrapped Hierarchical BLSTMs.

result Model outperforms state-of-the-art with macro F1-score of 0.785.

DDI Extraction Deep Learning Attention Mechanism Hierarchical BLSTM

2019-07-31abs ↗pdf ↗

Log Message Anomaly Detection and Classification Using Auto-B/LSTM and Auto-GRUcs.LG

Deep learning models detect and classify log anomalies.

problem Anomaly detection in unstructured log data.

method Auto-LSTM, Auto-BLSTM, and Auto-GRU models for feature extraction.

result Models outperform other algorithms on various log data sets.

log anomaly detection deep learning autoencoder log classification unstructured data

2019-11-20abs ↗pdf ↗

Sleep Stage Classification Based on Multi-level Feature Learning and Recurrent Neural Networks via Wearable Devicestat.ML

This paper proposes a practical approach for automatic sleep stage classification based on a multi-level feature learning framework and Recurrent Neural Network (RNN) classifier using heart rate and wrist actigraphy derived from a wearable device. The feature learning framework is designed to extract low- and mid-level…

2017-11-02abs ↗pdf ↗

GritNet: Student Performance Prediction with Deep Learningcs.LG

Student performance prediction - where a machine forecasts the future performance of students as they interact with online coursework - is a challenging problem. Reliable early-stage predictions of a student's future performance could be critical to facilitate timely educational interventions during a course. However, …

2018-04-19abs ↗pdf ↗

Automatic Speech Recognition for Humanitarian Applications in Somalics.CL

We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United Nations (UN) to implement keyword spotting systems supporting humanitarian relief…

2018-07-23abs ↗pdf ↗

Conformer-based Hybrid ASR System for Switchboard Datasetcs.CL

A hybrid ASR system using conformer architecture improves word-error-rate and training speed.

problem Improving word-error-rate and training efficiency for hybrid ASR systems.

method Used conformer architecture, applied time downsampling, and transposed convolutions.

result Conformer-based hybrid model achieves competitive results and significantly outperforms BLSTM-based hybrid model.

conformer hybrid ASR Switchboard dataset word-error-rate training speed

2021-11-05abs ↗pdf ↗

One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation of Text Datacs.LG

Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their innate ambiguity, a Word Sense Disambiguation (WSD) algorithm can avoid numbers…

2018-02-25abs ↗pdf ↗

Residual Memory Networks: Feed-forward approach to learn long temporal dependenciescs.CL

Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not poss…

2018-08-06abs ↗pdf ↗

Exploring the Robustness of NMT Systems to Nonsensical Inputscs.LG

Paper examines NMT robustness to nonsensical inputs.

problem NMT systems fail when source sentences are altered.

method Soft-attention technique to replace words in source sentences.

result Proposed technique achieves high success rate and outperforms existing methods.

NMT Robustness Nonsensical Inputs Soft-attention Adversarial Attacks

2019-08-03abs ↗pdf ↗

Towards Relevance and Sequence Modeling in Language Recognitioneess.AS

Neural network framework for language recognition considers sequence information and improves accuracy.

problem Challenging task of automatic language identification in noisy conditions.

method Proposes a neural network framework with bidirectional LSTM and attention modeling for relevance weighting.

result Significant improvements over conventional methods in noisy conditions and multi-speaker speech.

language recognition sequence modeling relevance weighting neural networks speech recognition

2020-04-02abs ↗pdf ↗

COVID19-HPSMP: COVID-19 Adopted Hybrid and Parallel Deep Information Fusion Framework for Stock Price Movement Predictionq-fin.ST

AI model predicts stock prices using social media data and hybrid neural networks.

problem Predicting stock price movements during the COVID-19 pandemic.

method Integrates social media trends and historical stock data using a hybrid CNN-BLSTM framework.

result The proposed framework outperforms traditional models in predicting stock price movements.

AI Machine Learning Deep Learning Stock Prediction Social Media

2021-01-02abs ↗pdf ↗

A Deep Learning Approach for Tweet Classification and Rescue Scheduling for Effective Disaster Managementcs.SI

Deep learning model classifies tweets for disaster rescue scheduling.

problem Efficiently processing and categorizing tweets for disaster rescue.

method Combining attention-based Bi-directional LSTM and CNN with pre-trained word vectors for classification and feature engineering.

result Proposed model outperforms other methods in Precision, Recall, F1-score, and Accuracy.

Deep Learning Tweet Classification Disaster Management Rescue Scheduling Social Media

2019-08-05abs ↗pdf ↗