Open Source German Distant Speech Recognition: Corpus and Acoustic Model

Radeck-Arneth, Stephan; Milde, Benjamin; Lange, Arvid; Gouvêa, Evandro B.; Radomski, Stefan; Mühlhäuser, Max; Biemann, Chris

doi:10.1007/978-3-319-24033-6_54

Cited by 23 publications

(9 citation statements)

References 16 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is the same dataset that was used to train the original Wav2Letter model. The German models were trained on several corpora taken from the Bavarian Archive for Speech Signals (BAS) (Schiel, 1998;Reichel et al, 2016) as well as the dataset described in Radeck-Arneth et al (2015), which will be referred to as "RADECK" from now on. Overall, we had a total of 383 hours of training data, which is only slightly more than one third of the English corpus.…”

Section: Datasetsmentioning

confidence: 99%

Transfer Learning for Speech Recognition on a Budget

Kunze¹,

Kirsch²,

Kurenkov³

et al. 2017

Proceedings of the 2nd Workshop on Representation Learning for NLP

View full text Add to dashboard Cite

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory, throughput and training data. We conduct several systematic experiments adapting a Wav2Letter convolutional neural network originally trained for English ASR to the German language. We show that this technique allows faster training on consumer-grade resources while requiring less training data in order to achieve the same accuracy, thereby lowering the cost of training ASR models in other languages. Model introspection revealed that small adaptations to the network's weights were sufficient for good performance, especially for inner layers.

show abstract

Section: Datasetsmentioning

confidence: 99%

Transfer Learning for Speech Recognition on a Budget

Kunze¹,

Kirsch²,

Kurenkov³

et al. 2017

Proceedings of the 2nd Workshop on Representation Learning for NLP

View full text Add to dashboard Cite

show abstract

“…To our knowledge, the largest freely available corpora for German-English speech translation comprise triples for 37 hours of German audio, German transcription, and English translation (Stüker et al, 2012). Pure speech recognition data are available from 36 hours (Radeck-Arneth et al, 2015) to around 200 hours (Baumann et al, 2018). We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audio books.…”

Section: Introductionmentioning

confidence: 99%

Learning multilingual named entity recognition from Wikipedia

Nothman

Ringland

Radford

et al. 2013

Artificial Intelligence

263

187

View full text Add to dashboard Cite

We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audio books. The corpus consists of over 100 hours of audio material and over 50k parallel sentences. The audio data is read speech and thus low in disfluencies. The quality of audio and sentence alignments has been checked by a manual evaluation, showing that speech alignment quality is in general very high. The sentence alignment quality is comparable to well-used parallel translation data and can be adjusted by cutoffs on the automatic alignment score. To our knowledge, this corpus is to date the largest resource for end-to-end speech translation for German.

show abstract

“…The proposed framework achieved a word error rate of 9.2%. Radeck-Arneth et al [258,259] collected corpus in a controlled and clean environment for German distant speech. A total of 36 h of the corpus were recorded from 180 different speakers.…”

Section: Germanmentioning

confidence: 99%

Computational intelligence in processing of speech acoustics: a survey

Singh

Kaur

Kukreja

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Speech recognition of a language is a key area in the field of pattern recognition. This paper presents a comprehensive survey on the speech recognition techniques for non-Indian and Indian languages, and compiled some of the computational models used for processing speech acoustics. An immense number of frameworks are available for speech processing and recognition for languages persisting around the globe. However, a limited number of automatic speech recognition systems are available for commercial use. The gap between the languages being spoken around the globe and the technical support available to these languages are very few. This paper examined major challenges for speech recognition for different languages. Analysis of the literature shows that lack of standard databases availability of minority languages hinder the research recognition research across the globe. When compared with non-Indian languages, the research on speech recognition of Indian languages (except Hindi) has not achieved the expected milestone yet. Combination of MFCC and DNN–HMM classifier is most commonly used system for developing ASR minority languages, whereas in some of the majority languages, researchers are using much advance algorithms of DNN. It has also been observed that the research in this field is quite thin and still more research needs to be carried out, particularly in the case of minority languages.

show abstract

Open Source German Distant Speech Recognition: Corpus and Acoustic Model

Cited by 23 publications

References 16 publications

Transfer Learning for Speech Recognition on a Budget

Transfer Learning for Speech Recognition on a Budget

Learning multilingual named entity recognition from Wikipedia

Computational intelligence in processing of speech acoustics: a survey

Contact Info

Product

Resources

About