Using the client device of a distributed speech recognizer usually implies the presence of background noise since most scenarios for distributed speech recognition (DSR) are situated in a non-office environment Thus, the general task is to choose the most suitable feature extraction method for the given conditions We present a hybrid speech recognition approach implemented for DSR that allows the choice of arbitrary feature vectors (regarding number and range of value) without changing the amount of data sent to the recognition engine Experiments were carried out using mel-cepstrum and RASTA-PLP features on the AURORA database Results show how the recognition performance under different noise conditions can be adjusted if the different features are combined, and that our hybrid approach to DSR has advantages that could not that easily be obtained with traditional DSR architectures

Flexible feature extraction and HMM design for a hybrid distributed speech recognition system in noisy environments

Hybrid NN/HMM acoustic modeling techniques for distributed speech recognition

Distributed speech recognition (DSR) where the recognizer is split up into two parts and connected via a transmission channel offers new perspectives for improving the speech recognition performance in mobile environments. In this work, we present the integration of hybrid acoustic models using tied-posteriors in a distributed environment. A comparison with standard Gaussian models is performed on the AURORA2 task and the WSJ0 task. Word-based HMMs and phoneme-based HMMs are trained for distributed and non-distributed recognition using either MFCC or RASTA-PLP features. The results show that hybrid modeling techniques can outperform standard continuous systems on this task. Especially the tied-posteriors approach is shown to be usable for DSR in a very flexible way since the client can be modified without a change at the server site and vice versa.

Das akustische Modell eines Spracherkenners basiert auf Methoden der statistischen Mustererkennung, um eine parametrische Reprasentation der gesprochenen Auserung zu ermoglichen. Zusammen mit einer Vorverarbeitung zur Datenreduktion, einem Worterbuch zur orthografisch korrekten Darstellung und einem Sprachmodell zur Eingrenzung wahrscheinlicher Worte ist das akustische Modell das Kernelement des Dekoders zur Konvertierung gesprochener Sprache in geschriebenen Text. Diese Arbeit beschreibt als Schwerpunkt die Elemente eines hybriden akustischen Modells mit verbundenen Auftrittswahrscheinlichkeiten (TP, engl. tied-posteriors) bestehend aus einem statischen Klassifikator und Hidden-Markov-Modellen (HMM). Vorteile des TP-Ansatzes sind eine grose Flexibilitat, sowie eine niedrigere Wortfehlerrate bei relativ wenigen, zu trainierenden Parametern. Als Beispiele fur geeignete statische Klassifikatoren werden neuronale Netze mit und ohne Ruckkopplung und Support-Vektor-Maschinen ausfuhrlich vorgestellt. Zur Verbesserung dieser neuronalen Netze sind neben der Phonem-, bzw. HMM-Zustandsklassifikation, Zusatzaufgaben parallel trainiert worden. Es hat sich als vorteilhaft herausgestellt, wenn zusatzlich das Geschlecht des Sprechers klassifiziert wird, da diese Aufgabe einfach zu lernen und unabhangig von der Lautklassifikation ist. Die Verwendung von SVM kann bisher nur bei sehr kleinem Vokabular (11 Zahlworter) evaluiert werden, da die Klassifikation mit mehreren SVM bislang sehr viel Rechenzeit erfordert. Dennoch lassen sich einige positive Tendenzen dieses Systems besonders bezuglich der Robustheit gegenuber Gerauschen erkennen. Neben den sprecherunabhangigen Systemen werden weiterhin Moglichkeiten prasentiert, die TP-Modelle an einen einzelnen Sprecher zu adaptieren. Erwahnenswert ist hierbei, das sowohl Parameter des Klassifikators (untersucht worden sind in dieser Arbeit neuronale Netze), als auch Parameter der HMM unabhangig voneinander und mit zusatzlichem Gewinn adaptiert werden konnen. Abschliesend bieten hybride akustische Modelle zusatzliche Anwendungsmoglichkeiten fur die verteilte Spracherkennung, bei der die Komponenten ortlich verteilt arbeiten und uber einen Kanal verbunden sind. Besonders die Flexibilitat bei der Veranderung einzelner Komponenten kann mit Gaus'schen akustischen Modellen nicht erreicht werden.

Automatische Spracherkennung mit hybriden akustischen Modellen

A comparison of traditional continuous speech recognizers with hybrid tied-posterior systems in distributed environments is presented for the first time on a challenging medium vocabulary task. We show how monophone and triphone systems are affected if speech features are sent over a wireless channel with limited bandwidth. The algorithms are evaluated on the Wall Street Journal database (WSJ0) and the results show that our monophone tied-posterior recognizer outperforms the traditional methods on this task by a dramatic reduction of the performance loss by a factor of 4 compared to nondistributed recognizers.

Distributed Speech Recognition on the WSJ task

Distributed speech recognition (DSR) is an interesting technology for mobile recognition tasks where the recognizer is split up into two parts and connected by a transmission channel. We compare the performance of standard and hybrid modeling approaches in this environment. The evaluation is done on clean and noisy speech samples taken from the TI digits and the Aurora databases. Our results show that, for this task, the hybrid modeling techniques can outperform standard continuous systems.

Comparison of standard and hybrid modeling techniques for distributed speech recognition

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

J. Stadermann

Author Tools

Chat about Author

Papers

Comparison of standard and hybrid modeling techniques for distributed speech recognition