Search Results for author: Mikko Kurimo

Found 42 papers, 9 papers with code

Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces

no code implementations NoDaLiDa 2021 Tuomas Kaseva, Hemant Kumar Kathania, Aku Rouhe, Mikko Kurimo

For children, the system trained on a large corpus of adult speakers performed worse than a system trained on a much smaller corpus of children’s speech.

Speaker Verification

Graph-based Syntactic Word Embeddings

no code implementations COLING (TextGraphs) 2020 Ragheb Al-Ghezi, Mikko Kurimo

We propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees.

POS Word Embeddings

Semiautomatic Speech Alignment for Under-Resourced Languages

no code implementations EURALI (LREC) 2022 Juho Leinonen, Niko Partanen, Sami Virpioja, Mikko Kurimo

Cross-language forced alignment is a solution for linguists who create speech corpora for very low-resource languages.

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

no code implementations COLING 2022 Khalid Alnajjar, Mika Hämäläinen, Jörg Tiedemann, Jorma Laaksonen, Mikko Kurimo

Our results show that the model is capable of correctly detecting whether an utterance is humorous 78% of the time and how long the audience's laughter reaction should last with a mean absolute error of 600 milliseconds.

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

no code implementations28 Oct 2022 Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri, Hemant Kathania, Mikko Kurimo

The current state-of-the-art methods proposed for these tasks are ensembles based on deep neural networks like ResNets in conjunction with feature engineering.

Feature Engineering

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

no code implementations10 Aug 2022 Georgios Karakasidis, Tamás Grósz, Mikko Kurimo

We hypothesize that end-to-end models can achieve better performance when provided with an organized training set consisting of examples that exhibit an increasing level of difficulty (i. e. a curriculum).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

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

no code implementations24 Mar 2022 Anssi Moisio, Dejan Porjazovski, Aku Rouhe, Yaroslav Getman, Anja Virkkunen, Tamás Grósz, Krister Lindén, Mikko Kurimo

The Donate Speech campaign has so far succeeded in gathering approximately 3600 hours of ordinary, colloquial Finnish speech into the Lahjoita puhetta (Donate Speech) corpus.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge

no code implementations6 Aug 2020 Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri, Hemant Kathania, Mikko Kurimo

On ComParE 2020 tasks, we investigate applying an ensemble of E2E models for robust performance and developing task-specific modifications for each task.

Feature Engineering

Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models

no code implementations LREC 2020 Mittul Singh, Peter Smit, Sami Virpioja, Mikko Kurimo

We, however, show that for character-based NNLMs, only pretraining with a related language improves the ASR performance, and using an unrelated language may deteriorate it.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Subword RNNLM Approximations for Out-Of-Vocabulary Keyword Search

1 code implementation28 May 2020 Mittul Singh, Sami Virpioja, Peter Smit, Mikko Kurimo

On these tasks, interpolating the baseline RNNLM approximation and a conventional LM outperforms the conventional LM in terms of the Maximum Term Weighted Value for single-character subwords.

speech-recognition Speech Recognition

Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

1 code implementation8 Apr 2020 Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo

There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; Subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary.

Data Augmentation Denoising +3

Finnish Language Modeling with Deep Transformer Models

no code implementations14 Mar 2020 Abhilash Jain, Aku Ruohe, Stig-Arne Grönroos, Mikko Kurimo

Transformers have recently taken the center stage in language modeling after LSTM's were considered the dominant model architecture for a long time.

Language Modelling

Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning

1 code implementation LREC 2020 Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo

Using English, Finnish, North Sami, and Turkish data sets, we show that this approach is able to find better solutions to the optimization problem defined by the Morfessor Baseline model than its original recursive training algorithm.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

A user study to compare two conversational assistants designed for people with hearing impairments

no code implementations WS 2019 Anja Virkkunen, Juri Lukkarila, Kalle Palom{\"a}ki, Mikko Kurimo

In the mobile device, augmented reality (AR) was used to help the hearing impaired observe gestures and lip movements of the speaker simultaneously with the transcriptions.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

TheanoLM - An Extensible Toolkit for Neural Network Language Modeling

no code implementations3 May 2016 Seppo Enarvi, Mikko Kurimo

We present a new tool for training neural network language models (NNLMs), scoring sentences, and generating text.

English Conversational Speech Recognition Language Modelling +1

Cannot find the paper you are looking for? You can Submit a new open access paper.