Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Optimizations of acoustic models for speech recognition applications on embedded systems
KTH, Skolan för informations- och kommunikationsteknik (ICT).
2017 (engelsk)Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
Abstract [en]

The primary focus of speech recognition systems is large vocabulary continuous speech. Nowadays most of the speech recognition platforms relies on high performance cloud computing solutions. However, when the operation of the system is required to work in off-line mode the embedded solution is preferable. An acoustic model for speech recognition is implemented based on an existing recurrent neural network model provided by EESEN framework.

The performance of automatic speech recognition has improved tremendously due to the application of RNNs for acoustic modelling and to their intrinsic ability to retain and use information from the past frames in order to understand correctly the meaning of the current input frame.

The Embedded GPU tegra k1 manufactured by Nvidia is used as target platform to accelerate the heavy computation step represented by the recurrent neural network forwarding pass. The basic implementation given by EESEN has been optimized for the specific hardware and profiled in order to evaluate performances in terms of both timing and power. The design methodology used for the Nvidia GPU has been applied to implement the same algorithm in OpenCL for FPGA. SDAccel tool from Xilinx enables the high level hardware synthesis starting from OpenCL code.

Experiments show that a significant speed up can be achieved compared to the basic implementation used in EESEN framework on both GPU and FPGA hardware. As regards to the power, GPU implementations do no guarantee considerable improvements as FPGA hardware does.

sted, utgiver, år, opplag, sider
2017. , s. 72
Serie
TRITA-ICT-EX ; 2017:33
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-219909OAI: oai:DiVA.org:kth-219909DiVA, id: diva2:1165908
Eksternt samarbeid
Politecnico di Torino
Fag / kurs
Information and Communication Technology
Utdanningsprogram
Master of Science in Engineering - Information and Communication Technology
Veileder
Examiner
Tilgjengelig fra: 2017-12-14 Laget: 2017-12-14 Sist oppdatert: 2018-01-13bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 94 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf