Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 25, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

475

Finnish parliament ASR corpus: Analysis, benchmarks and statistics.

Anja Virkkunen1, Aku Rouhe1, Nhan Phan1

  • 1Department of Information and Communications Engineering, Aalto University, Espoo, Finland.

Language Resources and Evaluation
|June 26, 2023
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Archival Research01:40

Archival Research

16.0K
Some researchers gain access to large amounts of data without interacting with a single research participant. Instead, they use existing records to answer various research questions. This type of research approach is known as archival research. Archival research relies on looking at past records or data sets to look for interesting patterns or relationships. For example, a researcher might access the academic records of all individuals who enrolled in college within the past ten years and...
16.0K
Statistical Analysis System (SAS)01:14

Statistical Analysis System (SAS)

238
SAS, short for Statistical Analysis System, is a powerful data analysis, management, and visualization tool. Developed by the SAS Institute in the early 1970s, SAS has evolved into a comprehensive software suite used across various industries for statistical analysis, business intelligence, and predictive modeling.
Applications: SAS finds applications in numerous fields, including healthcare for clinical trial analysis, finance for risk assessment, marketing for customer data analysis, and...
238
Statistical Analysis: Overview01:11

Statistical Analysis: Overview

6.7K
When we take repeated measurements on the same or replicated samples, we will observe inconsistencies in the magnitude. These inconsistencies are called errors. To categorize and characterize these results and their errors, the researcher can use statistical analysis to determine the quality of the measurements and/or suitability of the methods.
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
6.7K
Statistical Methods to Analyze Parametric Data: ANOVA01:12

Statistical Methods to Analyze Parametric Data: ANOVA

444
Analysis of Variance, or ANOVA, is a powerful statistical technique used to analyze parametric data, primarily in research and experimental studies. It's designed to compare the means of two or more groups, assisting researchers in identifying any significant differences between these group means. There are two main types of ANOVA based on the complexity of the analysis: one-way and two-way.
One-way ANOVA is applied when a single independent variable or factor is scrutinized. It compares...
444
One-Way ANOVA01:18

One-Way ANOVA

8.0K
One-way ANOVA analyzes more than three samples categorized by one factor. For example, it can compare the average mileage of sports bikes. Here, the data is categorized by one factor - the company. However, one-way ANOVA cannot be used to simultaneously compare the sample mean of three or more samples categorized by two factors. An example of two factors would be sports bikes from different companies driven in different terrains, such as a desert or snowy landscape. Here, two-way ANOVA is used...
8.0K
Two-Way ANOVA01:17

Two-Way ANOVA

2.7K
The two-way ANOVA is an extension of the one-way ANOVA. It is a statistical test performed on three or more samples categorized by two factors - a row factor and a column factor. Ronald Fischer mentioned it in 1925 in his book 'Statistical Methods for Researchers.'
The two-way ANOVA analysis initially begins by stating the null hypothesis that there is an interaction effect between the two factors of a dataset. This effect can be visualized using line segments formed by joining the...
2.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Self-Supervised App-Based Speech Training for Children With Speech Sound Disorder-A Single-Case Experimental Design Study.

International journal of language & communication disorders·2025
Same author

Listening like a speech-training app: Expert and non-expert listeners' goodness ratings of children's speech.

Clinical linguistics & phonetics·2024
Same author

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

Language resources and evaluation·2022
Same journal

The properties of panels in global comics: frequency and size of 76 K panels in 1,030 comics from 144 countries.

Language resources and evaluation·2026
Same journal

Towards a resource for multilingual lexicons: an MT assisted and human-in-the-loop multilingual parallel corpus with multi-word expression annotation.

Language resources and evaluation·2026
Same journal

OjibweMorph: an approachable finite-state transducer for Ojibwe (and beyond).

Language resources and evaluation·2026
Same journal

The narratives of war (NoW) corpus of written testimonies of the Russia-Ukraine war.

Language resources and evaluation·2025
Same journal

How different is different? Systematically identifying distribution shifts and their impacts in NER datasets.

Language resources and evaluation·2025
Same journal

Cross-linguistically consistent semantic and syntactic annotation of child-directed speech.

Language resources and evaluation·2025
See all related articles

The Finnish Parliament ASR Corpus offers extensive transcribed speech data for improving automatic speech recognition (ASR) systems. Analysis shows HMM-TDNN performance plateaus, while wav2vec 2.0 models benefit from more data.

Area of Science:

  • Speech Processing
  • Computational Linguistics
  • Machine Learning

Background:

  • Publicly available parliamentary recordings are valuable resources for training and evaluating automatic speech recognition (ASR) systems.
  • Existing datasets often lack sufficient scale or detailed metadata for robust ASR development.

Purpose of the Study:

  • To introduce and analyze the Finnish Parliament ASR Corpus, the largest publicly available Finnish speech dataset.
  • To establish benchmarks and evaluate various ASR system architectures on this corpus, considering longitudinal distribution shifts.

Main Methods:

  • Developed a Kaldi-based data preparation pipeline and ASR recipes for Hidden Markov Models (HMM), HMM-Deep Neural Networks (HMM-DNN), and Attention-Based Encoder-Decoders (AED).
  • Evaluated systems using time-delay neural networks (TDNN) and state-of-the-art wav2vec 2.0 pretrained acoustic models.
Keywords:
AEDFinnishHMM-DNNMetadataParliament speech dataSpeech recognitionWav2vec

More Related Videos

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data
08:35

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data

Published on: June 24, 2021

5.7K
Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R
06:01

Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R

Published on: December 9, 2022

2.6K

Related Experiment Videos

Last Updated: Jul 25, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

475
Identification of Alternative Splicing and Polyadenylation in RNA-seq Data
08:35

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data

Published on: June 24, 2021

5.7K
Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R
06:01

Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R

Published on: December 9, 2022

2.6K
  • Conducted comparative analyses on official and external test sets, including an equal data setting for HMM-DNN and AED.

    • Main Results:

    • The Finnish Parliament ASR Corpus contains over 3000 hours of speech from 449 speakers with demographic metadata.
    • HMM-TDNN ASR systems reached a performance plateau on official test sets, despite the corpus scale.
    • Larger wav2vec 2.0 models showed benefits from additional data, outperforming HMM-DNN in some scenarios.
    • HMM-DNN systems consistently outperformed AED systems in a matched data setting.

    Conclusions:

    • The Finnish Parliament ASR Corpus is a significant resource for advancing Finnish ASR research.
    • Investigated ASR performance trends and identified areas for improvement, particularly with large pretrained models.
    • Preliminary analysis suggests potential biases in ASR accuracy across different speaker demographics (gender, age, education).