search query: @keyword automatic speech recognition / total: 10
results-list
reference: 8 / 10
« previous | next »
Author:Mansikkaniemi, André
Title:Acoustic model and language model adaptation for a mobile dictation service
Adaptering av akustiska modeller och språkmodeller för en mobil dikteringstjänst
Publication type:Master's thesis
Publication year:2010
Pages:iv + 75 s. + liitt. 8      Language:   eng
Department/School:Elektroniikan, tietoliikenteen ja automaation tiedekunta
Main subject:Laskennallinen tekniikka   (S-114)
Supervisor:Sams, Mikko
Instructor:Kurimo, Mikko
Electronic version URL: http://urn.fi/URN:NBN:fi:aalto-201203131407
OEVS:
Electronic archive copy is available via Aalto Thesis Database.
Instructions
close

Reading digital theses in the closed network of the Aalto University Harald Herlin Learning Centre

In the closed network of Learning Centre you can read digital and digitized theses not available in the open network.

The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/

You can read theses on the Learning Centre customer computers, which are available on all floors.

Logging on to the customer computers

  • Aalto University staff members log on to the customer computer using the Aalto username and password.
  • Other customers log on using a shared username and password.

Opening a thesis

  • On the desktop of the customer computers, you will find an icon titled:

    Aalto Thesis Database

  • Click on the icon to search for and open the thesis you are looking for from Aaltodoc database. You can find the thesis file by clicking the link on the OEV or OEVS field.

Reading the thesis

  • You can either print the thesis or read it on the customer computer screen.
  • You cannot save the thesis file on a flash drive or email it.
  • You cannot copy text or images from the file.
  • You cannot edit the file.

Printing the thesis

  • You can print the thesis for your personal study or research use.
  • Aalto University students and staff members may print black-and-white prints on the PrintingPoint devices when using the computer with personal Aalto username and password. Color printing is possible using the printer u90203-psc3, which is located near the customer service. Color printing is subject to a charge to Aalto University students and staff members.
  • Other customers can use the printer u90203-psc3. All printing is subject to a charge to non-University members.
Location:P1 Ark Aalto  1166   | Archive
Keywords:automatic speech recognition
mobile dictation
acoustic model adaptation
language model adaptation
automatisk taligenk anning
mobil diktering
adaptering av akustiska modeller
adaptering av språkmodeller
Abstract (eng): Automatic speech recognition is the machine-based method of converting speech to text.
MobiDic is a mobile dictation service which uses a server-side speech recognition system to convert speech recorded on a mobile phone to readable and editable text notes.

In this work, performance of the TKK speech recognition system has been evaluated on law-related speech recorded on a mobile phone with the MobiDic client application.
There was mismatch between testing and training data in terms of both of acoustics and language.
The background acoustic models were trained on speech recorded on PC microphones.
The background language models were trained on texts from journals and news wire services.
Because of the special nature of the testing data, main focus has been on using acoustic model and language model adaptation methods to enhance speech recognition performance.

Acoustic model adaptation gives the highest and most reliable performance increase.
Using the global cMLLR method, word error rate reductions between 15-22% can be reached with only 2 minutes of adaptation data.
Regression class cMLLR can give even higher performance boosts if larger sets of audio adaptation data (> 10 min) are available.

Language model adaptation was not able to significantly improve performance in this task.
The main problems were differences between language adaptation data and language of the law-related speech data.
Abstract (swe): Automatisk taligenkänning är en maskinstyrd metod genom vilken tal omvandlas till text.
MobiDic är en mobil dikteringstjänst som använder ett serverbaserat automatiskt taligenkänningssystem för att omvandla tal inspelat på en mobiltelefon till läsbara och editerbara textdokument.
I detta arbete undersöktes förmågan hos Tekniska Högskolans taligenkänningssystem att omvandla juridik-relaterat tal inspelat på en mobiltelefon med MobiDics klientprogram till korrekt text.
Det fanns skillnader mellan test- och träningsdata gällande både akustik och språk.
De akutiska bakgrundsmodellerna var tränade med tal som hade spelats in på en datormikrofon.
Språkmodellerna var tränade med text från olika tidningar och nyhetstjänster.
På grund av testdatans speciella karaktär har tyngdpunkten i arbetet legat på att förbättra taligenkänningsförmågan hos systemet genom adaptering av akustiska modeller och språkmodeller.

Adaptering av akustiska modeller ger de bästa och pålitligaste resultaten i syftet att förbättra taligenkänningsförmågan.
Genom att använda den globala cMLLR-metoden och endast 2 minuter av adapteringsdata kan man förminska antalet feltolkade ord med 15-22%.
Genom att använda den regressionsklassbaserade cMLLR-metoden kan man uppnåytterligare förbättringar i taligenkänningsförmågan om det finns större mängder av adapteringsdata (> 10 min.) tillgängligt.

Adaptering av språkmodellen gav ingen betydande förbättring av taligenkännings förmågan.
Det främsta problemet var de stora skillnaderna mellan språkadapteringsdata och språket som förekom i de juridik-relaterade talinspelningarna.
ED:2010-04-07
INSSI record number: 39404
+ add basket
« previous | next »
INSSI