DE eng

Search in the Catalogues and Directories

Hits 1 – 14 of 14

1
Cross-lingual acoustic modeling in upper sorbian - preliminary study
In: Fraunhofer IKTS (2021)
Abstract: In this paper, we present a preliminary study for acoustic modeling in Upper Sorbian, where a model of German was used in cross-lingual transfer learning. At first, we define the grapheme and phoneme inventories and map the target phonemes from the most similar German source equivalents. Phonetically balanced sentences for the recording prompts were selected from a combination of general and domain-specific textual data. The speech corpora with a total duration of around 11 hours was collected in controlled recording sessions involving an equal number of females, males, and children. The baseline acoustic model was employed to force-align the speech corpora given the knowledge-based phoneme mappings. The goodness of the mappings was evaluated by the phoneme confusions in free-phoneme recognition. The new derived data-driven model with a reduced phoneme set was included in the adaptation and evaluation along with the baseline acoustic model. The model adaptation performance was cross-validated with the “Leave One Group Out” strategy. We observed major improvements in phoneme error rates after adaptation for the knowledge-based and data-driven phoneme mappings. The study confirmed the feasibility of transfer learning for acoustic model adaptation in the case of Upper Sorbian, at the same time demonstrating practical usability with a small vocabulary speech recognition application (Smart Lamp).
Keyword: acoustic modeling; speech recognition; Upper Sorbian
URL: http://publica.fraunhofer.de/documents/N-633297.html
BASE
Hide details
2
Glottal Stops in Upper Sorbian: A Data-Driven Approach
In: Fraunhofer IKTS (2021)
BASE
Show details
3
Reinforcement learning of minimalist grammars ...
BASE
Show details
4
Reinforcement Learning of Minimalist Numeral Grammars ...
BASE
Show details
5
Systemtheorie, Signalverarbeitung, Sprachtechnologie : Rüdiger Hoffmann zum 65. Geburtstag
Mehnert, Dieter (Herausgeber); Kordon, Ulrich (Herausgeber); Wolff, Matthias (Herausgeber). - Dresden : TUDpress, 2013
UB Frankfurt Linguistik
Show details
6
Elektronische Sprachsignalverarbeitung 2012 : Tagungsband der 23. Konferenz Cottbus, 29. - 31. August 2012
Wolff, Matthias (Hrsg.). - Dresden : TUDpress, 2012
UB Frankfurt Linguistik
Show details
7
Einkanalige Störgeräuschunterdrückung zur Steigerung der Worterkennungsrate eines Spracherkenners
In: Elektronische Sprachsignalverarbeitung. - Dresden : TUDpress 18 (2007), 52-59
BLLDB
Show details
8
Anwendung von Finite State Machines in der automatischen Sprachverarbeitung - Tutorium
In: Elektronische Sprachsignalverarbeitung. - Dresden : TUDpress 17 (2006), 205-207
BLLDB
Show details
9
Meta-classification for a language identification task
In: Electronic speech signal processing. - Dresden : TUDpress (2005), 346-355
BLLDB
Show details
10
Pronunciation variation modeling for spontaneous speech synthesis
In: Electronic speech signal processing. - Dresden : TUDpress (2005), 381-387
BLLDB
Show details
11
Toward spontaneous speech synthesis : utilizing language model information in TTS
In: Institute of Electrical and Electronics Engineers. IEEE transactions on speech and audio processing. - New York, NY : Inst. 12 (2004) 4, 436-445
BLLDB
Show details
12
Inverse Probleme in der Sprachsignalverarbeitung
In: Phonetics and its applications. - Stuttgart : Steiner (2002), 420-434
BLLDB
Show details
13
Tagungsband der elften Konferenz : Cottbus, 4. bis 6. September 2000
Fellbaum, Klaus (Hrsg.); Hess, Wolfgang (Mitarb.); Stöber, Karlheinz (Mitarb.)...
In: Elektronische Sprachsignalverarbeitung. - Dresden : TUDpress 11 (2000), 5-262
BLLDB
Show details
14
Automatische Generierung von Aussprachewörterbüchern aus Signaldaten
In: Computer, Linguistik und Phonetik zwischen Sprache und Sprechen. - Frankfurt am Main [u.a.] : Lang (1998), 213-225
BLLDB
Show details

Catalogues
2
0
0
0
0
0
0
Bibliographies
8
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
4
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern