On matching data and model in LF-MMI-based dysarthric speech recognition

Publications associées (28)

À propos
Confidentialité
Mentions légales

Graph Chatbot

Automatic Call Sign Detection: Matching Air Surveillance Data with Air Traffic Spoken Communications

Petr Motlicek, Amrutha Prasad

Voice communication is the main channel to exchange information between pilots and Air-Traffic Controllers (ATCos). Recently, several projects have explored the employment of speech recognition technology to automatically extract spoken key information suc ...

MDPI2021

Multitask adaptation with Lattice-Free MMI for multi-genre speech recognition of low resource languages

Hervé Bourlard, Petr Motlicek

In this paper, we develop Automatic Speech Recognition (ASR) systems for multi-genre speech recognition of low-resource languages where training data is predominantly conversational speech but test data can be in one of the following genres: news broadcast ...

ISCA-INT SPEECH COMMUNICATION ASSOC2021

Personalized Real-Time Federated Learning for Epileptic Seizure Detection

David Atienza Alonso, Amir Aminifar, Tomas Teijeiro Campo, Saleh Baghersalimi

Epilepsy is one of the most prevalent paroxystic neurological disorders. It is characterized by the occurrence of spontaneous seizures. About 1 out of 3 patients have drug-resistant epilepsy, thus their seizures cannot be controlled by medication. Automati ...

2021

Direction is what you need: Improving Word Embedding Compression in Large Language Models

Karl Aberer, Rémi Philippe Lebret, Mohammadreza Banaei

The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression of thes ...

ASSOC COMPUTATIONAL LINGUISTICS-ACL2021

Fast Transformers with Clustered Attention

François Fleuret, Angelos Katharopoulos, Apoorv Vyas

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making them prohibitivel ...

2020

Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages

Enno Hermann

Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good representation should ...

2021

Multilingual Training and Adaptation in Speech Recognition

Sibo Tong

State-of-the-art acoustic models for Automatic Speech Recognition (ASR) are based on Hidden Markov Models (HMM) and Deep Neural Networks (DNN) and often require thousands of hours of transcribed speech data during training. Therefore, building multilingual ...

EPFL2020

Dysarthric Speech Recognition with Lattice-Free MMI

Enno Hermann

Recognising dysarthric speech is a challenging problem as it differs in many aspects from typical speech, such as speaking rate and pronunciation. In the literature the focus so far has largely been on handling these variabilities in the framework of HMM/G ...

IEEE2020

Page 3 sur 3