Picture for Mikko Kurimo

Mikko Kurimo

On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation

Add code
Nov 14, 2023
Figure 1 for On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation
Figure 2 for On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation
Figure 3 for On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation
Figure 4 for On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation
Viaarxiv icon

Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference

Add code
Oct 16, 2023
Figure 1 for Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference
Figure 2 for Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference
Figure 3 for Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference
Viaarxiv icon

Topic Identification For Spontaneous Speech: Enriching Audio Features With Embedded Linguistic Information

Add code
Jul 21, 2023
Viaarxiv icon

When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity

Add code
Nov 03, 2022
Figure 1 for When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Figure 2 for When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Figure 3 for When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Figure 4 for When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
Viaarxiv icon

End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks

Add code
Oct 28, 2022
Figure 1 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Figure 2 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Figure 3 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Figure 4 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Viaarxiv icon

Comparison and Analysis of New Curriculum Criteria for End-to-End ASR

Add code
Aug 10, 2022
Figure 1 for Comparison and Analysis of New Curriculum Criteria for End-to-End ASR
Figure 2 for Comparison and Analysis of New Curriculum Criteria for End-to-End ASR
Figure 3 for Comparison and Analysis of New Curriculum Criteria for End-to-End ASR
Figure 4 for Comparison and Analysis of New Curriculum Criteria for End-to-End ASR
Viaarxiv icon

Finnish Parliament ASR corpus - Analysis, benchmarks and statistics

Add code
Mar 28, 2022
Figure 1 for Finnish Parliament ASR corpus - Analysis, benchmarks and statistics
Figure 2 for Finnish Parliament ASR corpus - Analysis, benchmarks and statistics
Figure 3 for Finnish Parliament ASR corpus - Analysis, benchmarks and statistics
Figure 4 for Finnish Parliament ASR corpus - Analysis, benchmarks and statistics
Viaarxiv icon

Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks

Add code
Mar 24, 2022
Figure 1 for Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks
Figure 2 for Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks
Figure 3 for Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks
Figure 4 for Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks
Viaarxiv icon

Data augmentation using prosody and false starts to recognize non-native children's speech

Add code
Aug 29, 2020
Figure 1 for Data augmentation using prosody and false starts to recognize non-native children's speech
Figure 2 for Data augmentation using prosody and false starts to recognize non-native children's speech
Figure 3 for Data augmentation using prosody and false starts to recognize non-native children's speech
Figure 4 for Data augmentation using prosody and false starts to recognize non-native children's speech
Viaarxiv icon

FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics

Add code
Aug 19, 2020
Figure 1 for FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics
Figure 2 for FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics
Figure 3 for FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics
Figure 4 for FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics
Viaarxiv icon