KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition

• URL: http://arxiv.org/abs/2009.03092v2
• Date: Sat, 26 Sep 2020 17:25:34 GMT
• Title: KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition
• Authors: Soohwan Kim, Seyoung Bae, Cheolhwang Won
• Abstract summary: KoSpeech is an end-to-end Korean automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch. We propose preprocessing methods for KsponSpeech corpus and a baseline model for benchmarks. Our baseline model achieved 10.31% character error rate (CER) at KsponSpeech corpus only with the acoustic model.
• Score: 1.7955614278088239
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present KoSpeech, an open-source software, which is modular and extensible end-to-end Korean automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch. Several automatic speech recognition open-source toolkits have been released, but all of them deal with non-Korean languages, such as English (e.g. ESPnet, Espresso). Although AI Hub opened 1,000 hours of Korean speech corpus known as KsponSpeech, there is no established preprocessing method and baseline model to compare model performances. Therefore, we propose preprocessing methods for KsponSpeech corpus and a baseline model for benchmarks. Our baseline model is based on Listen, Attend and Spell (LAS) architecture and ables to customize various training hyperparameters conveniently. By KoSpeech, we hope this could be a guideline for those who research Korean speech recognition. Our baseline model achieved 10.31% character error rate (CER) at KsponSpeech corpus only with the acoustic model. Our source code is available here.

Related papers

• SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models [58.996653700982556]
  Existing speech tokens are not specifically designed for speech language modeling. We propose SpeechTokenizer, a unified speech tokenizer for speech large language models. Experiments show that SpeechTokenizer performs comparably to EnCodec in speech reconstruction and demonstrates strong performance on the SLMTokBench benchmark.
  arXiv  Detail & Related papers  (2023-08-31T12:53:09Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• PolyVoice: Language Models for Speech to Speech Translation [50.31000706309143]
  PolyVoice is a language model-based framework for speech-to-speech translation (S2ST) We use discretized speech units, which are generated in a fully unsupervised way. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model.
  arXiv  Detail & Related papers  (2023-06-05T15:53:15Z)
• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling [92.55131711064935]
  We propose a cross-lingual neural language model, VALL-E X, for cross-lingual speech synthesis. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. It can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker's voice, emotion, and acoustic environment.
  arXiv  Detail & Related papers  (2023-03-07T14:31:55Z)
• ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus [3.1925030748447747]
  We present a speech corpus for Classical Arabic Text-to-Speech (ClArTTS) to support the development of end-to-end TTS systems for Arabic. The speech is extracted from a LibriVox audiobook, which is then processed, segmented, and manually transcribed and annotated. The final ClArTTS corpus contains about 12 hours of speech from a single male speaker sampled at 40100 kHz.
  arXiv  Detail & Related papers  (2023-02-28T20:18:59Z)
• SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training [106.34112664893622]
  We propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Our proposed SpeechUT is fine-tuned and evaluated on automatic speech recognition (ASR) and speech translation (ST) tasks.
  arXiv  Detail & Related papers  (2022-10-07T17:57:45Z)
• TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline [0.0]
  This paper introduces a new corpus of Mandarin-English code-switching speech recognition--TALCS corpus. TALCS corpus is derived from real online one-to-one English teaching scenes in TAL education group. To our best knowledge, TALCS corpus is the largest well labeled Mandarin-English code-switching open source automatic speech recognition dataset in the world.
  arXiv  Detail & Related papers  (2022-06-27T09:30:25Z)
• K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables [2.0813318162800707]
  K-Wav2Vec 2.0 is a modified version of Wav2vec 2.0 designed for Korean automatic speech recognition. In fine-tuning, we propose a multi-task hierarchical architecture to reflect the Korean writing structure. In pre-training, we attempted the cross-lingual transfer of the pre-trained model by further pre-training the English Wav2vec 2.0 on a Korean dataset.
  arXiv  Detail & Related papers  (2021-10-11T11:53:12Z)
• Jira: a Kurdish Speech Recognition System Designing and Building Speech Corpus and Pronunciation Lexicon [4.226093500082746]
  We introduce the first large vocabulary speech recognition system (LVSR) for the Central Kurdish language, named Jira. The Kurdish language is an Indo-European language spoken by more than 30 million people in several countries. Regarding speech corpus, we designed a sentence collection in which the ratio of di-phones in the collection resembles the real data of the Central Kurdish language. A test set including 11 different document topics is designed and recorded in two corresponding speech conditions.
  arXiv  Detail & Related papers  (2021-02-15T09:27:54Z)
• ESPnet-ST: All-in-One Speech Translation Toolkit [57.76342114226599]
  ESPnet-ST is a new project inside end-to-end speech processing toolkit, ESPnet. It implements automatic speech recognition, machine translation, and text-to-speech functions for speech translation. We provide all-in-one recipes including data pre-processing, feature extraction, training, and decoding pipelines.
  arXiv  Detail & Related papers  (2020-04-21T18:38:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.