paper-with-me

홈 › Papers

Subword and Crossword Units for CTC Acoustic Models

2017-12-19 · Thomas Zenkel, Ramon Sanabria, Florian Metze, Alex Waibel

This paper proposes a novel approach to create an unit set for CTC based speech recognition systems. By using Byte Pair Encoding we learn an unit set of an arbitrary size on a given training text. In contrast to using characters or words as units this allows us to find a good trade-off between the size of our unit set and the available training data. We evaluate both Crossword units, that may span multiple word, and Subword units. By combining this approach with decoding methods using a separate language model we are able to achieve state of the art results for grapheme based CTC systems.

📄 PDF Abstract BibTeX arXiv:1712.06855

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition

2021-04-19 · Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter 외

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM)…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Segmentationspeech-recognition+2

Crossword: Estimating Unknown Embeddings using Cross Attention and Alignment Strategies

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Word embedding methods like word2vec and GloVe have been shown to learn strong representations of words. However, these methods only learn representations for words in the training corpus. This is problematic, as model…

Word Embeddings

Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages

2020-07-29 · Siyuan Feng

(Short version of Abstract) This thesis describes an investigation on unsupervised acoustic modeling (UAM) for automatic speech recognition (ASR) in the zero-resource scenario, where only untranscribed speech data is ass…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Acquisitionspeech-recognition+1

Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation

2021-04-02 · Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez, Odette Scharenborg

This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a sub…

Acoustic Unit DiscoveryClustering

Improving the fusion of acoustic and text representations in RNN-T

2022-01-25 · Chao Zhang, Bo Li, Zhiyun Lu, Tara N. Sainath 외

The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR). To estimate the output distributions over subword units, RNN-T uses…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition